https://ramdi.fr/tags/ai/Recent content in Ai on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000https://ramdi.fr/github-stars/3d-re-gen-reconstructing-editable-3d-indoor-scenes-from-a-single-photo-with-multi-model-ai-orchestration/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/3d-re-gen-reconstructing-editable-3d-indoor-scenes-from-a-single-photo-with-multi-model-ai-orchestration/3D-RE-GEN reconstructs complete editable 3D indoor scenes from a single RGB photo. It integrates SAM, Hunyuan3D-2.0, and VGGT models in a modular Python pipeline.https://ramdi.fr/github-stars/a-practical-knowledge-base-for-mastering-stable-diffusion-and-generative-ai-workflows/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/a-practical-knowledge-base-for-mastering-stable-diffusion-and-generative-ai-workflows/Explore a curated repository of tutorials and workflows for Stable Diffusion, fine-tuning, ComfyUI, Automatic1111, and cloud execution. Ideal for hands-on AI practitioners.https://ramdi.fr/github-stars/ai-ml-cheatsheets-a-structured-collection-of-ai-and-machine-learning-reference-sheets/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/ai-ml-cheatsheets-a-structured-collection-of-ai-and-machine-learning-reference-sheets/AI-ML-Cheatsheets offers a modular, offline-ready collection of concise AI/ML reference sheets from foundational math to transformers and large language models.https://ramdi.fr/github-stars/apisr-a-python-toolkit-for-ai-based-image-and-video-super-resolution-with-practical-inference-modes/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/apisr-a-python-toolkit-for-ai-based-image-and-video-super-resolution-with-practical-inference-modes/APISR is a Python repo for AI-powered image and video super-resolution, offering fast Gradio inference and full-featured regular inference with dataset curation tools.https://ramdi.fr/github-stars/arkon-structured-enterprise-knowledge-synthesis-with-a-unique-llm-compilation-pipeline/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/arkon-structured-enterprise-knowledge-synthesis-with-a-unique-llm-compilation-pipeline/Arkon is a self-hosted enterprise knowledge hub using a novel MRP pipeline for structured, traceable wiki compilation with external AI inference and workspace-scoped RBAC.https://ramdi.fr/github-stars/automating-youtube-content-creation-with-youtube-automation-agent/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/automating-youtube-content-creation-with-youtube-automation-agent/Explore youtube-automation-agent, a Node.js tool that automates YouTube content creation using AI and the YouTube API. Setup is streamlined via an interactive wizard.https://ramdi.fr/github-stars/browserytools-136-browser-utilities-with-on-device-ai-in-a-next-js-monolith/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/browserytools-136-browser-utilities-with-on-device-ai-in-a-next-js-monolith/BrowseryTools packs over 136 browser utilities including on-device AI inference into a single Next.js app running fully client-side with zero backend or uploads.https://ramdi.fr/github-stars/building-an-ai-coding-assistant-in-go-inside-the-how-to-build-a-coding-agent-workshop/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/building-an-ai-coding-assistant-in-go-inside-the-how-to-build-a-coding-agent-workshop/Explore how the “how-to-build-a-coding-agent” Go workshop progressively constructs an AI coding assistant using an event loop and modular tool registry with the Anthropic Claude API.https://ramdi.fr/github-stars/bytez-unified-serverless-inference-across-220000-ai-models-with-a-single-api/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/bytez-unified-serverless-inference-across-220000-ai-models-with-a-single-api/Bytez offers a unified API for over 220,000 AI models with serverless GPU orchestration, abstracting model diversity into a single inference platform accessible via one key.https://ramdi.fr/github-stars/cairn-a-blackboard-driven-state-space-search-engine-with-stateless-agent-workers/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/cairn-a-blackboard-driven-state-space-search-engine-with-stateless-agent-workers/Cairn implements state-space search via a minimal blackboard architecture with stateless OODA loop workers. It scored perfectly at the Tencent AI Penetration Testing Challenge.https://ramdi.fr/github-stars/chattutor-enabling-ai-tutors-to-teach-stem-visually-with-a-vue-bun-full-stack/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/chattutor-enabling-ai-tutors-to-teach-stem-visually-with-a-vue-bun-full-stack/ChatTutor integrates AI tutors with visual tools like Geogebra in a Vue + Bun full-stack. It supports multiple LLM providers and offers a digital whiteboard for interactive STEM learning.https://ramdi.fr/github-stars/claude-office-integrating-claude-code-into-a-full-stack-typescript-environment/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/claude-office-integrating-claude-code-into-a-full-stack-typescript-environment/claude-office offers a TypeScript-based environment integrating Claude Code CLI with a backend and frontend, supporting AI enhancements. Quickstart commands enable fast setup.https://ramdi.fr/github-stars/claude-osint-turning-claude-into-an-ai-driven-osint-recon-operator-with-structured-skills/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/claude-osint-turning-claude-into-an-ai-driven-osint-recon-operator-with-structured-skills/Claude-OSINT equips Claude LLM with 4,600+ lines of structured OSINT tradecraft in markdown skills, enabling AI-driven recon with 90+ modules, 80+ dorks, and attack-path templates. No external APIs needed.https://ramdi.fr/github-stars/claudeblattman-a-no-code-ai-workflow-guide-for-academics-using-markdown-based-claude-code-skills/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/claudeblattman-a-no-code-ai-workflow-guide-for-academics-using-markdown-based-claude-code-skills/claudeblattman is an open-source guide that teaches academics to build practical AI workflows with Claude Code using markdown-based skills—no coding required.https://ramdi.fr/github-stars/codex-autoresearch-structured-ai-driven-optimization-loops-with-multi-session-state/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/codex-autoresearch-structured-ai-driven-optimization-loops-with-multi-session-state/Codex Autoresearch structures vague improvement goals into measured AI-driven optimization loops with durable multi-session state and live dashboard insights.https://ramdi.fr/github-stars/conar-an-ai-powered-multi-database-sql-ide-in-an-electron-desktop-app/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/conar-an-ai-powered-multi-database-sql-ide-in-an-electron-desktop-app/Conar is an Electron desktop app offering AI-assisted SQL editing for PostgreSQL, MySQL, MSSQL, and Clickhouse with encrypted cloud-stored connections and multiple AI model support.https://ramdi.fr/github-stars/deepdiagram-streaming-xml-driven-ai-visualization-with-multi-agent-orchestration/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/deepdiagram-streaming-xml-driven-ai-visualization-with-multi-agent-orchestration/DeepDiagram uses a streaming XML tag output pattern with LangGraph multi-agent orchestration to transform natural language into diagrams in real-time. It features React 19 + FastAPI and supports multimodal inputs.https://ramdi.fr/github-stars/exploring-the-awesome-production-agentic-systems-repository-a-curated-catalog-of-production-ready-ai-agentic-systems/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/exploring-the-awesome-production-agentic-systems-repository-a-curated-catalog-of-production-ready-ai-agentic-systems/The awesome-production-agentic-systems repo is a curated list of production-ready AI agentic systems, helping developers navigate the growing ecosystem of autonomous AI agents.https://ramdi.fr/github-stars/fun-asr-alibaba-s-multilingual-speech-recognition-model-with-real-time-capabilities/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/fun-asr-alibaba-s-multilingual-speech-recognition-model-with-real-time-capabilities/Fun-ASR is Alibaba Tongyi Lab’s end-to-end speech recognition model with 800M parameters, supporting 31 languages and real-time transcription in noisy environments.https://ramdi.fr/github-stars/fuzzyai-ai-driven-fuzz-testing-with-local-llm-integration/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/fuzzyai-ai-driven-fuzz-testing-with-local-llm-integration/FuzzyAI combines fuzz testing with AI models using Python and Ollama. It offers a CLI for fuzzing with local LLMs, balancing AI power and practical setup tradeoffs.https://ramdi.fr/github-stars/gimp-mcp-enabling-ai-driven-image-editing-with-live-feedback-via-model-context-protocol/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/gimp-mcp-enabling-ai-driven-image-editing-with-live-feedback-via-model-context-protocol/GIMP MCP bridges GIMP 3.2 with AI assistants via MCP, offering 56 tool commands and live PNG snapshots for AI-driven iterative image editing workflows.https://ramdi.fr/github-stars/halovoice-browser-based-real-time-ai-voice-translation-with-cloud-processing/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/halovoice-browser-based-real-time-ai-voice-translation-with-cloud-processing/HaloVoice offers real-time AI voice translation in the browser with sub-200ms latency using cloud AI. It supports 30+ languages and integrates as a system mic for apps like Discord and Zoom.https://ramdi.fr/github-stars/how-claude-wordpress-skills-brings-ai-powered-wordpress-code-reviews-to-claude-code/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/how-claude-wordpress-skills-brings-ai-powered-wordpress-code-reviews-to-claude-code/claude-wordpress-skills packages professional WordPress engineering skills as Claude Code plugins, enabling AI-assisted performance reviews and best practice guidance via slash commands and natural language triggers.https://ramdi.fr/github-stars/how-narratorai-cli-skill-orchestrates-ai-agents-for-automated-movie-narration/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/how-narratorai-cli-skill-orchestrates-ai-agents-for-automated-movie-narration/NarratorAI CLI Skill uses a machine-readable SKILL.md file to enable AI agents to automate movie narration video production via a CLI tool. Supports multiple agents and rich media resources.https://ramdi.fr/github-stars/how-socrates-skill-turns-claude-ai-into-a-socratic-tutor-with-prompt-engineering/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/how-socrates-skill-turns-claude-ai-into-a-socratic-tutor-with-prompt-engineering/Socrates-skill transforms Claude into a Socratic tutor using a 5-step questioning workflow in a plain-text skill. Learn how prompt engineering drives guided learning without code.https://ramdi.fr/github-stars/html-anything-a-local-first-agentic-html-editor-orchestrating-multiple-coding-agents-through-composable-skills/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/html-anything-a-local-first-agentic-html-editor-orchestrating-multiple-coding-agents-through-composable-skills/html-anything routes 75 composable SKILL.md templates through 8 CLI coding agents for live HTML generation streamed into a sandboxed iframe, with zero API keys required.https://ramdi.fr/github-stars/idea-validation-agents-markdown-driven-ai-venture-analyst-with-rigorous-validation-scoring/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/idea-validation-agents-markdown-driven-ai-venture-analyst-with-rigorous-validation-scoring/idea-validation-agents is a zero-install markdown-driven AI framework for indie devs, featuring a unique multiplicative-floor scoring system for startup idea validation workflows.https://ramdi.fr/github-stars/inside-claude-code-s-typescript-plugin-suite-for-ai-powered-frontend-workflows/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/inside-claude-code-s-typescript-plugin-suite-for-ai-powered-frontend-workflows/Explore Claude Code’s TypeScript plugins offering specialized AI agents and commands for modern web development, with easy setup and workflow automation.https://ramdi.fr/github-stars/inside-everything-claude-code-ecc-a-multi-agent-ai-coding-orchestration-runtime-evolving-in-rust/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/inside-everything-claude-code-ecc-a-multi-agent-ai-coding-orchestration-runtime-evolving-in-rust/ECC is a performance optimization system for AI coding agents, now evolving into a Rust-based orchestration runtime managing 60 agents and 232 skills across 12 languages.https://ramdi.fr/github-stars/inside-everything-claude-code-ecc-ai-coding-agent-orchestration-evolving-in-rust/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/inside-everything-claude-code-ecc-ai-coding-agent-orchestration-evolving-in-rust/Everything Claude Code (ECC) is a performance optimization system managing 60 AI coding agents and 232 skills across 12 languages, now evolving into a Rust-based orchestration runtime.https://ramdi.fr/github-stars/inside-google-cloud-ai-s-agent-platform-an-end-to-end-operating-system-for-enterprise-ai-agents/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/inside-google-cloud-ai-s-agent-platform-an-end-to-end-operating-system-for-enterprise-ai-agents/Explore Google Cloud AI’s Agent Platform, a full-stack solution spanning foundation models, development kits, open protocols, and governance for enterprise AI agents.https://ramdi.fr/github-stars/llm-mm-agent-autonomous-mathematical-modeling-with-hierarchical-method-selection/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/llm-mm-agent-autonomous-mathematical-modeling-with-hierarchical-method-selection/LLM-MM-Agent uses LLMs as autonomous agents for end-to-end mathematical modeling, featuring a unique hierarchical method library with actor-critic selection. Supports GPT-4o and DeepSeek-R1.https://ramdi.fr/github-stars/macai-a-unified-native-macos-ai-chat-client-for-multiple-llm-providers/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/macai-a-unified-native-macos-ai-chat-client-for-multiple-llm-providers/macai is a native macOS AI chat client unifying access to major LLM providers with iCloud Sync and local inference support, offering a minimalist cross-device AI chat experience.https://ramdi.fr/github-stars/meridian-a-local-proxy-bridging-claude-code-sdk-and-anthropic-compatible-ai-tools/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/meridian-a-local-proxy-bridging-claude-code-sdk-and-anthropic-compatible-ai-tools/Meridian is a TypeScript local proxy that translates Claude Code SDK calls into an Anthropic-compatible API, enabling seamless use of Claude Max with third-party AI coding tools without OAuth hacks.https://ramdi.fr/github-stars/mini-wiki-ai-powered-incremental-wiki-documentation-generation-with-instruction-based-plugins/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/mini-wiki-ai-powered-incremental-wiki-documentation-generation-with-instruction-based-plugins/Mini-Wiki enables AI agents to generate and maintain structured wiki docs from codebases incrementally, using a safe instruction-based plugin system. Supports Mermaid diagrams and multi-language output.https://ramdi.fr/github-stars/minimalist-python-ai-demos-exploring-qxresearch-event-1-s-concise-llm-patterns/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/minimalist-python-ai-demos-exploring-qxresearch-event-1-s-concise-llm-patterns/qxresearch-event-1 is a collection of 50+ minimalist Python apps showcasing core AI patterns like fine-tuning, vector DB, and Whisper in about 10 lines each. A practical learning resource.https://ramdi.fr/github-stars/navigating-ai-learning-with-bishwaghimire-s-ai-learning-roadmaps/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/navigating-ai-learning-with-bishwaghimire-s-ai-learning-roadmaps/A practical guide to bishwaghimire’s AI learning roadmaps repository, offering modular, career-focused paths for AI and ML self-learners, with setup essentials and a flexible curriculum.https://ramdi.fr/github-stars/navigating-the-ai-plugin-explosion-in-obsidian-with-awesome-obsidian-ai-tools/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/navigating-the-ai-plugin-explosion-in-obsidian-with-awesome-obsidian-ai-tools/Explore a curated directory listing 86 AI plugins for Obsidian, revealing the shift from cloud chatbots to privacy-focused local LLM integrations and the sprawling AI plugin landscape.https://ramdi.fr/github-stars/navigating-the-evolving-landscape-of-llm-based-multi-agent-systems-a-survey-paper-repository/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/navigating-the-evolving-landscape-of-llm-based-multi-agent-systems-a-survey-paper-repository/A curated and frequently updated bibliography accompanying the IJCAI 2024 survey paper on LLM-based multi-agent systems, organizing research into five key categories and revealing emerging trends.https://ramdi.fr/github-stars/oh-my-product-multi-agent-orchestration-for-google-s-gemini-cli-via-tmux/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/oh-my-product-multi-agent-orchestration-for-google-s-gemini-cli-via-tmux/oh-my-product extends Google’s Gemini CLI with multi-agent orchestration using tmux and slash commands for parallel AI workflows, offering persistent state and lifecycle controls.https://ramdi.fr/github-stars/open-computer-use-orchestrating-multi-model-llm-pipelines-for-remote-linux-desktop-control/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/open-computer-use-orchestrating-multi-model-llm-pipelines-for-remote-linux-desktop-control/Open Computer Use uses a modular three-stage LLM pipeline to control a cloud Linux desktop, combining grounding, vision, and action models for flexible AI-driven automation.https://ramdi.fr/github-stars/openclaw-a-swiftui-ios-app-for-real-time-voice-ai-and-media-management/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/openclaw-a-swiftui-ios-app-for-real-time-voice-ai-and-media-management/OpenClaw is a native iOS SwiftUI app integrating real-time voice AI conversations, audiobooks, podcasts, and academic paper management with ElevenLabs Conversational AI and WebRTC.https://ramdi.fr/github-stars/opendirectory-a-modular-skills-library-for-ai-agents-with-targeted-installation/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/opendirectory-a-modular-skills-library-for-ai-agents-with-targeted-installation/OpenDirectory provides a Python-based collection of AI agent skills with an npm CLI for browsing and installing skills targeted at specific AI agents like Claude Code or Codex.https://ramdi.fr/github-stars/openkoto-a-privacy-focused-ai-powered-desktop-language-learning-app-with-tauri-and-rust/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/openkoto-a-privacy-focused-ai-powered-desktop-language-learning-app-with-tauri-and-rust/OpenKoto is an AI-powered desktop language learning app built with Tauri, React, and Rust, offering local processing for privacy and native performance across 100+ languages.https://ramdi.fr/github-stars/opskat-ai-first-secure-infrastructure-management-with-policy-enforced-ai-agents/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/opskat-ai-first-secure-infrastructure-management-with-policy-enforced-ai-agents/OpsKat is a desktop app blending AI agents with secure, policy-enforced remote infrastructure control across SSH, databases, and Kafka. It bridges AI coding assistants to production safely.https://ramdi.fr/github-stars/orchestrator-supaconductor-ai-driven-project-orchestration-plugin-for-claude-code/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/orchestrator-supaconductor-ai-driven-project-orchestration-plugin-for-claude-code/orchestrator-supaconductor is a Python plugin for Claude Code that automates software project workflows via natural language commands, managing sprints, coding, and testing interactively.https://ramdi.fr/github-stars/pai-a-portable-privacy-first-debian-live-usb-os-for-offline-ai-work/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/pai-a-portable-privacy-first-debian-live-usb-os-for-offline-ai-work/pai is a bootable Debian 12 live USB OS optimized for offline AI inference with Ollama, running entirely in RAM with privacy features and minimal footprint.https://ramdi.fr/github-stars/pentest-agents-a-cross-ide-autonomous-bug-bounty-framework-with-multi-agent-ai/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/pentest-agents-a-cross-ide-autonomous-bug-bounty-framework-with-multi-agent-ai/pentest-agents deploys 50 specialized AI agents across 7 coding tools with a multi-IDE portability layer, autonomous exploit chains, endpoint brain, and MCP servers for bug bounty hunting.https://ramdi.fr/github-stars/pm-claude-skills-modular-professional-workflows-as-claude-ai-skills-in-markdown/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/pm-claude-skills-modular-professional-workflows-as-claude-ai-skills-in-markdown/pm-claude-skills is a large open-source library of 135 markdown skills for Claude AI, spanning 16 professions and multi-agent templates with data connectors for automated workflows.https://ramdi.fr/github-stars/prompt-engineering-jumpstart-a-practical-pattern-based-guide-to-mastering-prompt-engineering-fundamentals/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/prompt-engineering-jumpstart-a-practical-pattern-based-guide-to-mastering-prompt-engineering-fundamentals/Prompt-Engineering-Jumpstart is an open-source eBook teaching 14 core prompt engineering patterns with practical examples, aimed at non-technical AI users and emphasizing universal AI interaction grammar.https://ramdi.fr/github-stars/reasoningbank-experience-driven-memory-as-a-new-scaling-dimension-for-ai-agents/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/reasoningbank-experience-driven-memory-as-a-new-scaling-dimension-for-ai-agents/ReasoningBank introduces memory-aware test-time scaling for AI agents by storing reasoning traces from both successes and failures, enabling self-evolution through experience.https://ramdi.fr/github-stars/reverse-engineering-claude-code-an-open-source-playbook-for-ai-coding-agent-prompts/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/reverse-engineering-claude-code-an-open-source-playbook-for-ai-coding-agent-prompts/This repo reverse-engineers Claude Code’s AI coding agent prompts into reusable templates covering safety, tool routing, multi-agent coordination, and memory management for practical prompt engineering.https://ramdi.fr/github-stars/skill-conductor-architecture-first-lifecycle-management-for-ai-agent-skills/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/skill-conductor-architecture-first-lifecycle-management-for-ai-agent-skills/Skill Conductor enforces design patterns and uses a 5-mode lifecycle to manage AI agent skills, avoiding common pitfalls like the ‘description trap’ for more reliable skill development.https://ramdi.fr/github-stars/superclaude-meta-programming-claude-code-into-a-structured-ai-development-platform/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/superclaude-meta-programming-claude-code-into-a-structured-ai-development-platform/SuperClaude transforms Claude Code into a structured AI development platform using behavioral instruction injection, 30 slash commands, 20 specialized agents, and 8 MCP server integrations for faster, token-efficient workflows.https://ramdi.fr/github-stars/theanimescripter-a-unified-multi-backend-ai-video-enhancement-toolkit-with-efficient-model-chaining/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/theanimescripter-a-unified-multi-backend-ai-video-enhancement-toolkit-with-efficient-model-chaining/TheAnimeScripter wraps dozens of AI video models behind one CLI and AE plugin, supporting CUDA, TensorRT, DirectML, OpenVINO backends. Model chaining avoids redundant disk writes.https://ramdi.fr/github-stars/unity-skills-ai-driven-automation-engine-for-unity-editor-with-enterprise-grade-safety/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/unity-skills-ai-driven-automation-engine-for-unity-editor-with-enterprise-grade-safety/Unity-Skills offers AI-driven Unity Editor automation with 750 skills, server-side permission modes, and transactional atomicity for safe multi-step operations.https://ramdi.fr/github-stars/visomaster-fusion-a-portable-windows-app-bundling-multiple-ai-face-swapping-models/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/visomaster-fusion-a-portable-windows-app-bundling-multiple-ai-face-swapping-models/VisoMaster Fusion bundles over a dozen AI face-swapping models into a portable Windows desktop app with automatic runtime setup, simplifying the complex AI video editing workflow.https://ramdi.fr/github-stars/weave-a-go-microkernel-platform-for-hot-pluggable-ai-application-development/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/weave-a-go-microkernel-platform-for-hot-pluggable-ai-application-development/Weave is a Go-based AI platform with a microkernel architecture that supports hot-pluggable AI plugins and dynamic multi-model switching. Deploy with Docker Compose for rapid development.https://ramdi.fr/github-stars/minds-platform-an-enterprise-grade-ai-foundation-for-autonomous-agents-and-semantic-search/Fri, 15 May 2026 14:23:51 +0000https://ramdi.fr/github-stars/minds-platform-an-enterprise-grade-ai-foundation-for-autonomous-agents-and-semantic-search/Minds Platform offers a Python-based AI foundation with autonomous agents and semantic search, designed for flexible enterprise deployment across cloud and on-prem environments.https://ramdi.fr/github-stars/aider-precise-ai-pair-programming-with-whole-codebase-awareness/Sat, 09 May 2026 11:42:26 +0000https://ramdi.fr/github-stars/aider-precise-ai-pair-programming-with-whole-codebase-awareness/Aider is a terminal-based AI pair programming tool that builds a repository map for full codebase context, enabling precise, developer-controlled edits with multi-LLM support and git integration.https://ramdi.fr/github-stars/holyclaude-a-battle-tested-docker-ai-dev-workstation-solving-real-container-quirks/Sat, 09 May 2026 11:42:26 +0000https://ramdi.fr/github-stars/holyclaude-a-battle-tested-docker-ai-dev-workstation-solving-real-container-quirks/HolyClaude bundles Claude Code, 7 AI CLIs, a headless browser, and 50+ dev tools in a Docker container that fixes 15+ real-world Docker quirks, enabling AI dev setup in 30 seconds.https://ramdi.fr/github-stars/inside-claude-code-from-scratch-a-practical-reconstruction-of-anthropic-s-coding-agent/Sat, 09 May 2026 11:42:26 +0000https://ramdi.fr/github-stars/inside-claude-code-from-scratch-a-practical-reconstruction-of-anthropic-s-coding-agent/Claude Code From Scratch distills Anthropic’s 500K+ line coding agent into ~8,000 lines of Python and TypeScript, revealing core architecture like the Agent Loop, semantic memory, multi-agent skills, and context compression.https://ramdi.fr/github-stars/milvus-a-distributed-vector-database-with-go-orchestration-and-c-search-engine/Sat, 09 May 2026 11:42:26 +0000https://ramdi.fr/github-stars/milvus-a-distributed-vector-database-with-go-orchestration-and-c-search-engine/Milvus is an open-source distributed vector database with a Go system layer and C++ core, supporting multiple vector indexes, hybrid search, and Kubernetes-native scaling for AI workloads.https://ramdi.fr/github-stars/olares-building-a-personal-cloud-os-on-kubernetes-for-local-ai-and-app-hosting/Wed, 06 May 2026 18:58:37 +0000https://ramdi.fr/github-stars/olares-building-a-personal-cloud-os-on-kubernetes-for-local-ai-and-app-hosting/Olares combines Kubernetes with over 30 open-source projects to create a personal cloud OS focused on data sovereignty, local AI, and sandboxed apps.https://ramdi.fr/github-stars/command-code-an-ai-coding-agent-that-learns-your-coding-taste-with-meta-neuro-symbolic-ai/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/command-code-an-ai-coding-agent-that-learns-your-coding-taste-with-meta-neuro-symbolic-ai/Command Code uses a meta neuro-symbolic AI ’taste-1’ model to continuously learn and adapt to your coding style, enabling personalized full-stack project building and bug fixing.https://ramdi.fr/github-stars/langfuse-simplifying-llm-observability-with-decorator-based-tracing/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/langfuse-simplifying-llm-observability-with-decorator-based-tracing/Langfuse provides end-to-end observability for LLM applications with automatic tracing via an @observe() decorator, enabling teams to debug and manage AI workflows efficiently.https://ramdi.fr/github-stars/little-coder-a-coding-agent-optimized-for-small-local-language-models/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/little-coder-a-coding-agent-optimized-for-small-local-language-models/little-coder adapts AI coding agents to run efficiently on small local language models, achieving strong benchmark results with minimal setup.https://ramdi.fr/github-stars/pulse-ai-powered-unified-monitoring-for-proxmox-docker-and-kubernetes/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/pulse-ai-powered-unified-monitoring-for-proxmox-docker-and-kubernetes/Pulse is a Go-based self-hosted dashboard that unifies monitoring for Proxmox, Docker, and Kubernetes. It features AI-driven health checks detecting silent failures in homelab infrastructure.https://ramdi.fr/github-stars/quivr-a-python-framework-for-flexible-retrieval-augmented-generation-pipelines/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/quivr-a-python-framework-for-flexible-retrieval-augmented-generation-pipelines/Quivr is a Python framework offering an opinionated, pluggable retrieval-augmented generation pipeline with multi-LLM support and YAML-defined workflows for flexible knowledge retrieval.https://ramdi.fr/github-stars/softaworks-agent-toolkit-a-modular-plugin-marketplace-for-ai-coding-agents/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/softaworks-agent-toolkit-a-modular-plugin-marketplace-for-ai-coding-agents/Softaworks Agent Toolkit offers 40+ modular AI skills and plugins for coding agents like Claude Code, enabling composable AI workflows via a plugin marketplace. Here’s how it works.https://ramdi.fr/github-stars/goal-driven-orchestrating-long-lived-ai-agents-with-prompt-based-verification-loops/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/goal-driven-orchestrating-long-lived-ai-agents-with-prompt-based-verification-loops/Goal-Driven offers a prompt-based master-subagent architecture to sustain long-running AI problem-solving sessions through a verification-driven orchestration loop without code or frameworks.https://ramdi.fr/github-stars/how-kiln-orchestrates-multi-agent-ai-workflows-using-markdown-and-claude-code/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/how-kiln-orchestrates-multi-agent-ai-workflows-using-markdown-and-claude-code/Kiln implements a 7-step multi-agent AI pipeline entirely through markdown files and Claude Code’s native primitives, avoiding any runtime or package dependencies.https://ramdi.fr/github-stars/how-obsidian-second-brain-transforms-your-obsidian-vault-into-an-ai-maintained-knowledge-base/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/how-obsidian-second-brain-transforms-your-obsidian-vault-into-an-ai-maintained-knowledge-base/obsidian-second-brain rewrites Obsidian vault pages autonomously using Claude Code agents, detecting contradictions and running scheduled maintenance for a self-healing AI knowledge base.https://ramdi.fr/github-stars/inside-santifer-cv-santiago-a-production-grade-ai-powered-portfolio-with-robust-security-and-evaluation/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/inside-santifer-cv-santiago-a-production-grade-ai-powered-portfolio-with-robust-security-and-evaluation/santifer/cv-santiago offers an interactive portfolio CV with a dual-mode AI chatbot, hybrid search, multi-layer prompt injection defenses, and a closed-loop evaluation pipeline for production-grade AI security.https://ramdi.fr/github-stars/mapping-the-ai-agent-self-evolution-ecosystem-with-the-awesome-agent-evolution-taxonomy/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/mapping-the-ai-agent-self-evolution-ecosystem-with-the-awesome-agent-evolution-taxonomy/The awesome-agent-evolution repo organizes 50+ open-source projects into a clear taxonomy of AI agent self-evolution and infrastructure layers, offering a practical ecosystem map for developers.https://ramdi.fr/github-stars/orca-orchestrating-multiple-ai-coding-agents-with-git-worktree-isolation/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/orca-orchestrating-multiple-ai-coding-agents-with-git-worktree-isolation/Orca is a cross-platform IDE that runs multiple AI coding agents in isolated Git worktrees, enabling parallel development without branch conflicts. Subscription-agnostic and feature-rich.https://ramdi.fr/github-stars/skillclaw-a-modular-python-framework-for-orchestrating-ai-agents-across-openai-compatible-and-aws-bedrock-apis/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/skillclaw-a-modular-python-framework-for-orchestrating-ai-agents-across-openai-compatible-and-aws-bedrock-apis/SkillClaw is a Python framework enabling flexible AI agent orchestration across OpenAI-compatible and AWS Bedrock APIs, focusing on modularity and provider-agnostic design.https://ramdi.fr/github-stars/snip-a-visual-feedback-layer-for-ai-coding-agents-with-local-ai-processing/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/snip-a-visual-feedback-layer-for-ai-coding-agents-with-local-ai-processing/Snip enhances AI coding agents by rendering visual outputs and enabling spatial annotations as structured feedback. It runs all AI locally, supporting multiple agents and offering a CLI and MCP server.https://ramdi.fr/github-stars/standardizing-ai-agent-workflows-with-xcrawl-skills-for-web-data-apis/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/standardizing-ai-agent-workflows-with-xcrawl-skills-for-web-data-apis/xcrawl-skills defines standardized AI agent skills with normalized inputs/outputs for web data tasks like scraping and crawling via the XCrawl API. It enables multi-agent orchestration with minimal integration.https://ramdi.fr/github-stars/alibaba-s-qwen3-6-efficient-large-scale-llms-with-gated-delta-networks-and-sparse-moe/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/alibaba-s-qwen3-6-efficient-large-scale-llms-with-gated-delta-networks-and-sparse-moe/Qwen3.6 from Alibaba uses gated delta networks and sparse Mixture-of-Experts to achieve near-397B parameter model performance with only 3B active parameters, supporting 201 languages and 262k context length.https://ramdi.fr/github-stars/automating-faceless-video-content-creation-with-ai-workflows-and-syllaby-io/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/automating-faceless-video-content-creation-with-ai-workflows-and-syllaby-io/Explore how this guide and course structure the automation of faceless video content creation using AI tools, focusing on workflow, multi-platform scheduling, and monetization strategies.https://ramdi.fr/github-stars/building-machine-learning-intuition-through-engineering-analogies-with-thereisnospoon/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/building-machine-learning-intuition-through-engineering-analogies-with-thereisnospoon/There Is No Spoon offers a unique ML primer for software engineers, using physical analogies to build deep intuition for neural networks and architectures beyond memorization.https://ramdi.fr/github-stars/building-production-ready-rag-workflows-with-n8n-using-free-json-templates/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/building-production-ready-rag-workflows-with-n8n-using-free-json-templates/Explore over 200 pre-built n8n workflow templates integrating vector databases, embedding models, and LLMs for rapid RAG workflow prototyping and deployment without coding.https://ramdi.fr/github-stars/claude-code-hooks-audible-notifications-for-ai-agent-lifecycle-events/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/claude-code-hooks-audible-notifications-for-ai-agent-lifecycle-events/Claude Code Hooks maps Claude Code AI agent lifecycle events to audio signals, providing developers with real-time audible feedback for 27 agent states without terminal watching.https://ramdi.fr/github-stars/codeburn-local-first-cli-for-multi-provider-ai-coding-session-cost-and-productivity-tracking/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/codeburn-local-first-cli-for-multi-provider-ai-coding-session-cost-and-productivity-tracking/CodeBurn is a local CLI tool parsing session data from 18 AI coding assistants to provide token cost and task tracking via a TUI dashboard, with no cloud dependency.https://ramdi.fr/github-stars/mapping-the-generative-ai-landscape-with-the-ai-collection-curated-directory/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/mapping-the-generative-ai-landscape-with-the-ai-collection-curated-directory/Explore ai-collection, a comprehensive curated directory mapping 30+ categories of generative AI tools. Understand its structure, strengths, and how it helps navigate a fragmented AI market.https://ramdi.fr/github-stars/open-researcher-ai-powered-web-research-assistant-with-integrated-scraping-and-summarization/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/open-researcher-ai-powered-web-research-assistant-with-integrated-scraping-and-summarization/open-researcher is a TypeScript app combining AI APIs and web scraping to assist research workflows. It offers an extensible setup and local dev server for experimentation.https://ramdi.fr/github-stars/postiz-a-temporal-powered-ai-assisted-social-media-scheduler-with-agent-cli-integration/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/postiz-a-temporal-powered-ai-assisted-social-media-scheduler-with-agent-cli-integration/Postiz is an open-source, self-hosted social media scheduler built with Temporal workflows, AI content generation, and multi-platform API integrations. It supports an agent CLI and automation platform connectors.https://ramdi.fr/github-stars/abtop-process-based-monitoring-of-ai-coding-agents-in-rust-with-tmux-integration/Mon, 04 May 2026 10:23:03 +0000https://ramdi.fr/github-stars/abtop-process-based-monitoring-of-ai-coding-agents-in-rust-with-tmux-integration/abtop is a Rust TUI that monitors local AI coding agents by scanning processes and files without API keys. Supports macOS, Linux, Windows with tmux pane jumping and colorblind themes.https://ramdi.fr/github-stars/inside-open-docs-reverse-engineering-the-internals-of-ai-cli-coding-agents/Mon, 04 May 2026 10:23:03 +0000https://ramdi.fr/github-stars/inside-open-docs-reverse-engineering-the-internals-of-ai-cli-coding-agents/Open-docs reverse-engineers major AI CLI coding agents to reveal undocumented internals, security models, and integration patterns. A deep dive for developers building on these agents.https://ramdi.fr/github-stars/skillhub-desktop-unifying-ai-coding-assistant-skills-with-a-rust-react-tauri-app/Mon, 04 May 2026 10:23:03 +0000https://ramdi.fr/github-stars/skillhub-desktop-unifying-ai-coding-assistant-skills-with-a-rust-react-tauri-app/SkillHub Desktop tackles fragmentation in AI coding assistants by unifying skill management across tools using a Rust backend and React frontend via Tauri. One-click multi-tool skill installs.https://ramdi.fr/github-stars/agent-skills-by-sleekdotdesign-modular-ai-agent-skills-for-programmatic-mobile-app-design/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/agent-skills-by-sleekdotdesign-modular-ai-agent-skills-for-programmatic-mobile-app-design/Explore agent-skills by sleekdotdesign, an AI agent skill enabling programmatic mobile app design with Sleek API. Modular, CLI-driven, niche but practical for AI tooling.https://ramdi.fr/github-stars/agent-startup-kit-reusable-ai-coding-workflows-as-skill-playbooks-for-saas-dev/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/agent-startup-kit-reusable-ai-coding-workflows-as-skill-playbooks-for-saas-dev/agent-startup-kit offers a modular set of AI-assisted coding workflows for SaaS, packaged as reusable skill playbooks for Claude Code and VS Code.https://ramdi.fr/github-stars/claude-cowork-guide-practical-ai-workflows-and-plugin-docs-for-business-users/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/claude-cowork-guide-practical-ai-workflows-and-plugin-docs-for-business-users/A detailed guide to Claude Cowork, Anthropic’s desktop AI assistant, offering 28 business workflows, 70 prompts, and plugin docs for knowledge workers and small businesses.https://ramdi.fr/github-stars/docsgpt-a-flexible-ai-platform-for-private-agents-and-enterprise-document-search/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/docsgpt-a-flexible-ai-platform-for-private-agents-and-enterprise-document-search/DocsGPT is a Python-based AI platform for building private agents and enterprise search, with multi-LLM support and versatile deployment modes via Docker Compose.https://ramdi.fr/github-stars/dotnet-skills-a-curated-marketplace-of-ai-agent-skills-for-the-net-ecosystem/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/dotnet-skills-a-curated-marketplace-of-ai-agent-skills-for-the-net-ecosystem/dotnet/skills offers 11 AI coding assistant plugins covering the full .NET stack, following the agentskills.io standard for cross-platform AI agent integration. Easy install via CLI or IDE.https://ramdi.fr/github-stars/edit-mind-orchestrating-multi-modal-ai-pipelines-for-local-first-semantic-video-search/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/edit-mind-orchestrating-multi-modal-ai-pipelines-for-local-first-semantic-video-search/Edit Mind indexes video libraries with multi-modal AI pipelines and stores embeddings for semantic search. Its Docker Compose microservices orchestrate transcription, object, and face recognition for scene-level queries.https://ramdi.fr/github-stars/embedding-opencode-ai-in-obsidian-a-pragmatic-approach-to-ai-assistant-integration/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/embedding-opencode-ai-in-obsidian-a-pragmatic-approach-to-ai-assistant-integration/Explore how opencode-obsidian embeds the OpenCode AI assistant into Obsidian via a web view, balancing implementation simplicity with UI limitations.https://ramdi.fr/github-stars/exploring-ai-agent-skills-as-design-systems-for-ui-development-in-awesome-ai-tools-for-ui/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/exploring-ai-agent-skills-as-design-systems-for-ui-development-in-awesome-ai-tools-for-ui/A curated list of 30+ AI-powered tools and agent skills for UI/UX development, showcasing how SKILL.md files serve as new design systems for AI-driven design consistency.https://ramdi.fr/github-stars/exploring-axton-obsidian-visual-skills-ai-powered-diagram-skills-for-obsidian/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/exploring-axton-obsidian-visual-skills-ai-powered-diagram-skills-for-obsidian/axton-obsidian-visual-skills offers prompt-based Claude Code Skills to generate Excalidraw, Mermaid, and Canvas diagrams in Obsidian, as a lightweight alternative to MCP servers.https://ramdi.fr/github-stars/exploring-claude-api-integration-patterns-with-anthropics-claude-cookbooks/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/exploring-claude-api-integration-patterns-with-anthropics-claude-cookbooks/anthropics/claude-cookbooks offers Jupyter Notebook recipes demonstrating practical Claude API usage, including sub-agent orchestration, multimodal vision, and RAG patterns.https://ramdi.fr/github-stars/fire-enrich-a-sequential-multi-agent-pipeline-for-enriched-company-profiles-from-emails/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/fire-enrich-a-sequential-multi-agent-pipeline-for-enriched-company-profiles-from-emails/Fire Enrich orchestrates 5 specialized AI agents in sequence to enrich company profiles from email addresses, using Next.js, OpenAI, and Firecrawl.https://ramdi.fr/github-stars/fireworks-tech-graph-natural-language-to-production-ready-ai-and-uml-diagrams-with-embedded-visual-styles/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/fireworks-tech-graph-natural-language-to-production-ready-ai-and-uml-diagrams-with-embedded-visual-styles/fireworks-tech-graph is a Claude Code skill that generates production-quality SVG and PNG technical diagrams from natural language, supporting 7 visual styles and 14 UML types plus AI agent patterns.https://ramdi.fr/github-stars/generating-architecture-diagrams-as-standalone-html-with-claude-ai-skills/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/generating-architecture-diagrams-as-standalone-html-with-claude-ai-skills/This repo uses a Claude AI skill to generate dark-themed system architecture diagrams as self-contained HTML/SVG files with zero dependencies, using semantic color coding and prompt engineering.https://ramdi.fr/github-stars/gigabrain-a-modular-ai-agent-tooling-plugin-for-openclaw-and-claude-code/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/gigabrain-a-modular-ai-agent-tooling-plugin-for-openclaw-and-claude-code/gigabrain is a Node.js plugin that extends OpenClaw and AI toolchains like Codex and Claude Code, providing setup and verification utilities for AI agent workflows.https://ramdi.fr/github-stars/graymatter-a-modular-mcp-server-for-local-first-ai-prompt-packages/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/graymatter-a-modular-mcp-server-for-local-first-ai-prompt-packages/Graymatter is a Go-based MCP server managing modular prompt packages for AI agents like Claude Code, offering local-first lazy loading and easy integration with AI CLIs.https://ramdi.fr/github-stars/heygen-com-skills-modular-ai-agent-skills-for-avatar-and-video-generation/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/heygen-com-skills-modular-ai-agent-skills-for-avatar-and-video-generation/heygen-com/skills offers modular AI agent skills to create digital avatars and videos from photos, integrating with multiple coding agents via an agent-driven install pattern.https://ramdi.fr/github-stars/how-the-claude-plugins-repo-orchestrates-multi-agent-ai-consultation-with-multiple-llms/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/how-the-claude-plugins-repo-orchestrates-multi-agent-ai-consultation-with-multiple-llms/claude-plugins is a TypeScript-based plugin marketplace for Claude Code, featuring a multi-agent consultant plugin that runs parallel LLMs like GPT-5, Gemini, Grok, Perplexity, and Claude for AI consultation.https://ramdi.fr/github-stars/how-video-use-turns-ai-agents-into-transcript-driven-video-editors/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/how-video-use-turns-ai-agents-into-transcript-driven-video-editors/video-use replaces frame-heavy editing with transcript-driven AI agents, using ElevenLabs Scribe and self-evaluation to produce polished edits.https://ramdi.fr/github-stars/injecting-domain-expertise-into-claude-ai-a-deep-dive-into-the-email-marketing-bible-skill/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/injecting-domain-expertise-into-claude-ai-a-deep-dive-into-the-email-marketing-bible-skill/Explore how the email-marketing-bible Claude Code skill injects 68,000 words of sourced email marketing expertise into Claude AI, enabling expert audits, copywriting, and automation advice.https://ramdi.fr/github-stars/inside-openclaw-claude-bridge-a-translation-layer-bridging-openclaw-and-claude-code-cli/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/inside-openclaw-claude-bridge-a-translation-layer-bridging-openclaw-and-claude-code-cli/openclaw-claude-bridge translates OpenClaw’s OpenAI API calls into Claude Code CLI’s native protocol, managing persistent sessions and tool-call conversions with a React dashboard for real-time metrics.https://ramdi.fr/github-stars/isc-bench-exposing-fundamental-ai-safety-failures-from-workflow-level-design/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/isc-bench-exposing-fundamental-ai-safety-failures-from-workflow-level-design/ISC-Bench reveals a structural AI safety flaw where LLMs produce harmful outputs to complete tasks, bypassing prompt-level defenses. It benchmarks this workflow-level vulnerability across top models.https://ramdi.fr/github-stars/llm-god-orchestrating-multiple-llm-web-uis-in-one-electron-app-with-dom-injection/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/llm-god-orchestrating-multiple-llm-web-uis-in-one-electron-app-with-dom-injection/LLM-God bundles multiple LLM web interfaces into a single Electron app, using DOM injection to send prompts to all models simultaneously. It offers a clever free-tier workaround with tradeoffs.https://ramdi.fr/github-stars/llm-wikid-agent-agnostic-ai-knowledge-base-with-schema-driven-compilation-for-obsidian/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/llm-wikid-agent-agnostic-ai-knowledge-base-with-schema-driven-compilation-for-obsidian/llm-wikid uses a CLAUDE.md schema to control a multi-phase ingest pipeline compiling markdown wiki pages for Obsidian, offering better Q&A at scale than RAG. Supports multiple AI agents and quality checks.https://ramdi.fr/github-stars/magi-a-structured-multi-llm-debate-system-with-iterative-critique-and-voting/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/magi-a-structured-multi-llm-debate-system-with-iterative-critique-and-voting/MAGI implements a multi-round debate protocol among three LLMs to match stronger models’ accuracy via iterative critique and voting. It offers fault tolerance, adaptive escalation, and persona presets.https://ramdi.fr/github-stars/mapping-the-ai-agent-orchestration-landscape-with-an-awesome-curated-list/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/mapping-the-ai-agent-orchestration-landscape-with-an-awesome-curated-list/A curated list catalogs 80+ AI coding agent orchestration tools, revealing a fragmented ecosystem around git worktree isolation, parallel execution, and multi-agent coordination.https://ramdi.fr/github-stars/mapping-the-open-source-ai-stack-with-the-awesome-opensource-ai-curated-list/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/mapping-the-open-source-ai-stack-with-the-awesome-opensource-ai-curated-list/A curated directory cataloging over 200 production-ready open-source AI projects across the machine learning stack, from training frameworks to self-hosted UIs.https://ramdi.fr/github-stars/memary-recursive-knowledge-graph-memory-for-autonomous-ai-agents/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/memary-recursive-knowledge-graph-memory-for-autonomous-ai-agents/Memary is an open-source memory layer for AI agents using knowledge graphs and recursive retrieval to efficiently store and query agent memories. It supports multi-agent setups and integrates with LlamaIndex and OpenAI.https://ramdi.fr/github-stars/memex-a-local-first-ai-native-knowledge-management-app-with-custom-multi-agent-orchestration/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/memex-a-local-first-ai-native-knowledge-management-app-with-custom-multi-agent-orchestration/Memex is a Flutter-based local-first personal knowledge app using multi-agent AI to organize and extract insights. It supports custom agents with event-driven triggers and 14+ LLM providers.https://ramdi.fr/github-stars/meta-ads-kit-automated-ai-driven-management-of-meta-ads-campaigns/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/meta-ads-kit-automated-ai-driven-management-of-meta-ads-campaigns/meta-ads-kit automates Meta Ads workflows with an AI agent CLI tool, replacing manual dashboard work with AI-driven monitoring, fatigue detection, copy generation, and direct Graph API uploads.https://ramdi.fr/github-stars/mex-cli-tool-for-ai-prompt-and-codebase-synchronization/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/mex-cli-tool-for-ai-prompt-and-codebase-synchronization/mex is a TypeScript CLI that helps keep AI prompts in sync with your codebase by scanning your project and managing drift with simple commands.https://ramdi.fr/github-stars/ok-skills-a-universal-skill-pack-for-ai-coding-agents/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/ok-skills-a-universal-skill-pack-for-ai-coding-agents/ok-skills provides 38 reusable SKILL.md playbooks for AI coding agents like Claude Code and Cursor, standardizing cross-agent skill portability with AGENTS.md triggers.https://ramdi.fr/github-stars/open-carrusel-a-local-ai-powered-instagram-carousel-builder-with-claude-code-subprocess/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/open-carrusel-a-local-ai-powered-instagram-carousel-builder-with-claude-code-subprocess/Open Carrusel is a local-first Instagram carousel builder using Claude Code as an AI subprocess to generate HTML/CSS slides. It exports pixel-perfect PNGs via Puppeteer, all without cloud dependencies.https://ramdi.fr/github-stars/openclaw-auto-dream-sleep-inspired-memory-consolidation-for-persistent-ai-agents/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/openclaw-auto-dream-sleep-inspired-memory-consolidation-for-persistent-ai-agents/OpenClaw Auto-Dream implements a 5-layer memory model with importance scoring and forgetting curves to consolidate AI agent memories like human sleep. It enables persistent, evolving knowledge.https://ramdi.fr/github-stars/openclaw-mission-control-centralized-monitoring-for-openclaw-ai-agents-with-a-typescript-dashboard/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/openclaw-mission-control-centralized-monitoring-for-openclaw-ai-agents-with-a-typescript-dashboard/openclaw-mission-control is a TypeScript project offering a centralized dashboard to monitor and control OpenClaw AI agents. It hooks into OpenClaw to provide real-time visibility and management.https://ramdi.fr/github-stars/openpostings-self-hosted-ats-aggregator-with-ai-driven-job-application-automation/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/openpostings-self-hosted-ats-aggregator-with-ai-driven-job-application-automation/OpenPostings aggregates 500k daily jobs from 60+ ATS providers into a local app with AI-powered application automation via an MCP apply-agent server.https://ramdi.fr/github-stars/operationalizing-classic-software-engineering-wisdom-for-ai-coding-agents-with-agent-rules-books/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/operationalizing-classic-software-engineering-wisdom-for-ai-coding-agents-with-agent-rules-books/agent-rules-books converts classic software engineering book rules into context-budgeted Markdown sets for AI coding agents, balancing timeless principles with AI token limits.https://ramdi.fr/github-stars/pai-opencode-modular-multi-agent-ai-infrastructure-with-smart-model-routing/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/pai-opencode-modular-multi-agent-ai-infrastructure-with-smart-model-routing/PAI-OpenCode offers a modular AI infrastructure with 16 specialized agents and smart model routing across 75+ providers, optimizing performance and cost with a minimal 20KB core.https://ramdi.fr/github-stars/ppt-as-code-structuring-ai-powered-presentation-workflows-with-a-dual-mode-visual-workbench/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/ppt-as-code-structuring-ai-powered-presentation-workflows-with-a-dual-mode-visual-workbench/PPT-as-code structures presentation creation into staged AI-driven steps with a visual workbench that supports both deck-model and direct HTML editing. It balances pipeline rigor with visual flexibility.https://ramdi.fr/github-stars/resume-matcher-a-provider-agnostic-ai-platform-for-tailored-resumes-using-litellm-abstraction/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/resume-matcher-a-provider-agnostic-ai-platform-for-tailored-resumes-using-litellm-abstraction/Resume Matcher uses LiteLLM to unify six LLM providers for AI-powered resume tailoring, with a FastAPI backend and Next.js frontend. It supports local and cloud deployments with PDF export.https://ramdi.fr/github-stars/safestclaw-combining-simple-ai-setup-with-automated-security-scanning-in-python/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/safestclaw-combining-simple-ai-setup-with-automated-security-scanning-in-python/SafestClaw offers a Python CLI tool that simplifies AI model configuration and automates security scanning across projects. It supports cloud and local AI models with zero YAML config editing.https://ramdi.fr/github-stars/signal-an-open-source-ai-sales-intelligence-platform-with-browser-automation-for-enrichment/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/signal-an-open-source-ai-sales-intelligence-platform-with-browser-automation-for-enrichment/Signal is an open-source AI sales intelligence platform that detects buying signals, enriches contacts via browser automation, and manages multi-step outreach. It uses Next.js, Supabase, and Anthropic Claude.https://ramdi.fr/github-stars/skillforge-efficient-ai-skill-management-for-claude-code-and-codex/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/skillforge-efficient-ai-skill-management-for-claude-code-and-codex/SkillForge v5.1 reduces AI skill prompt size by 64% using context-efficient design and trigger-based routing in Claude Code and Codex environments.https://ramdi.fr/github-stars/station-a-go-runtime-for-multi-agent-ai-orchestration-with-mcp-stdio-bridging/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/station-a-go-runtime-for-multi-agent-ai-orchestration-with-mcp-stdio-bridging/Station is an open-source Go runtime that orchestrates multi-agent AI systems on self-hosted infrastructure using a Git-backed workflow and MCP stdio bridging. It supports 41 AI tools and multiple AI providers.https://ramdi.fr/github-stars/vam-seek-client-side-2d-video-timeline-navigation-with-temporal-rgb-encoding/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/vam-seek-client-side-2d-video-timeline-navigation-with-temporal-rgb-encoding/VAM Seek replaces 1D video scrubbing with a client-side 2D thumbnail grid using Canvas API and an LRU cache. It features VAM-RGB temporal encoding for AI perception.https://ramdi.fr/github-stars/viseron-a-modular-self-hosted-ai-video-surveillance-platform/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/viseron-a-modular-self-hosted-ai-video-surveillance-platform/Viseron is a self-hosted, local-only AI NVR platform in Python with modular AI features for privacy-focused video surveillance. Runs fully locally with Docker deployment.https://ramdi.fr/github-stars/xurl-a-unified-cli-abstraction-for-multi-agent-ai-workflows-with-a-custom-uri-scheme/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/xurl-a-unified-cli-abstraction-for-multi-agent-ai-workflows-with-a-custom-uri-scheme/xURL offers a Rust-based CLI that unifies multiple AI agent CLIs under a single agents:// URI scheme, enabling consistent conversation management across providers.https://ramdi.fr/github-stars/a-practical-taxonomy-for-large-language-model-ensembles-exploring-the-awesome-llm-ensemble-repository/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/a-practical-taxonomy-for-large-language-model-ensembles-exploring-the-awesome-llm-ensemble-repository/The Awesome-LLM-Ensemble repo catalogs research on combining multiple LLMs with a clear three-phase taxonomy: before, during, and after inference ensemble methods.https://ramdi.fr/github-stars/applypilot-autonomous-ai-driven-job-application-pipeline-with-modular-architecture-and-advanced-automation/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/applypilot-autonomous-ai-driven-job-application-pipeline-with-modular-architecture-and-advanced-automation/ApplyPilot automates job applications using AI scoring, resume tailoring, and Playwright-driven form submissions across multiple job boards and portals. It features a modular, parallel pipeline and CAPTCHA handling.https://ramdi.fr/github-stars/automating-professional-svg-logo-generation-with-a-structured-ai-workflow/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/automating-professional-svg-logo-generation-with-a-structured-ai-workflow/This Claude Code skill generates 6+ professional SVG logo variants through a 5-phase AI-driven workflow and produces high-quality showcases using Gemini 3.1. It blends design rigor with automation.https://ramdi.fr/github-stars/blinko-an-open-source-privacy-first-ai-note-taking-app-with-rag-powered-local-search/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/blinko-an-open-source-privacy-first-ai-note-taking-app-with-rag-powered-local-search/Blinko is a self-hosted AI note-taking app using RAG for natural language search over local Markdown notes. Cross-platform, privacy-first, deployable via Docker one-liner.https://ramdi.fr/github-stars/claude-hub-autonomous-ai-driven-github-workflows-with-container-isolation-and-webhook-security/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/claude-hub-autonomous-ai-driven-github-workflows-with-container-isolation-and-webhook-security/claude-hub bridges Claude Code with GitHub for autonomous AI development workflows, featuring container isolation, multi-auth support, and CI/CD monitoring via webhooks.https://ramdi.fr/github-stars/claude-shorts-ai-driven-pipeline-for-viral-vertical-video-clips-from-long-form-content/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/claude-shorts-ai-driven-pipeline-for-viral-vertical-video-clips-from-long-form-content/claude-shorts uses AI scoring, GPU transcription, and adaptive video reframing to extract viral-ready vertical clips from long videos, optimizing cuts with audio-aware snapping and platform-specific encoding.https://ramdi.fr/github-stars/claudish-a-versatile-typescript-cli-proxy-bridging-claude-code-with-580-ai-models/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/claudish-a-versatile-typescript-cli-proxy-bridging-claude-code-with-580-ai-models/Claudish is a TypeScript CLI proxy that lets Claude Code work with 580+ AI models via OpenRouter, direct APIs, and local inference, enabling multimodal capabilities through vision proxying.https://ramdi.fr/github-stars/curating-quality-a-curated-list-of-essential-books-for-large-language-model-engineers/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/curating-quality-a-curated-list-of-essential-books-for-large-language-model-engineers/A curated list of 24 rigorously selected books on LLM engineering, covering foundational theory to production deployment. Highlights a unique 6-step quality filtering process.https://ramdi.fr/github-stars/datagen-a-langgraph-multi-agent-framework-for-automated-data-analysis-workflows/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/datagen-a-langgraph-multi-agent-framework-for-automated-data-analysis-workflows/DATAGEN orchestrates eight specialized AI agents using LangGraph to automate data analysis workflows with progressive disclosure and multi-LLM provider support.https://ramdi.fr/github-stars/drawio-skill-pure-skill-md-ai-agent-skill-for-professional-draw-io-diagrams-with-self-checking/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/drawio-skill-pure-skill-md-ai-agent-skill-for-professional-draw-io-diagrams-with-self-checking/drawio-skill generates professional draw.io diagrams from natural language using pure SKILL.md with a unique self-check and iterative refinement loop across 6 agent platforms.https://ramdi.fr/github-stars/egregore-persistent-multi-agent-collaboration-with-claude-code-hooks-and-git-based-shared-memory/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/egregore-persistent-multi-agent-collaboration-with-claude-code-hooks-and-git-based-shared-memory/egregore uses Claude Code hooks and git-based shared memory to enable persistent, multi-agent collaboration without daemons or network calls. A shell script driven, version-controlled protocol.https://ramdi.fr/github-stars/inside-claude-code-writer-building-a-multi-platform-ai-content-pipeline-with-claude-code-agents/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/inside-claude-code-writer-building-a-multi-platform-ai-content-pipeline-with-claude-code-agents/claude-code-writer uses Claude Code slash commands and specialized agents to automate content creation from raw ideas to platform-specific formats, maintaining voice consistency across LinkedIn, newsletters, Twitter, and podcasts.https://ramdi.fr/github-stars/lmms-lab-writer-a-local-first-ai-powered-latex-editor-with-on-the-fly-package-management/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/lmms-lab-writer-a-local-first-ai-powered-latex-editor-with-on-the-fly-package-management/LMMs-Lab Writer is a native LaTeX editor built with Tauri that automates LaTeX package installs during compilation and integrates AI editing and Git, all running fully offline.https://ramdi.fr/github-stars/mco-orchestrating-multiple-ai-coding-agents-through-a-neutral-cli-layer/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/mco-orchestrating-multiple-ai-coding-agents-through-a-neutral-cli-layer/MCO is a Python CLI tool that orchestrates multiple AI coding agents in parallel, aggregating results with deduplication and consensus, enabling multi-agent review workflows from any AI IDE.https://ramdi.fr/github-stars/mind-map-wizard-ai-powered-mind-maps-with-a-custom-svg-rendering-engine/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/mind-map-wizard-ai-powered-mind-maps-with-a-custom-svg-rendering-engine/Mind-Map-Wizard generates interactive mind maps from AI-generated markdown outlines using a custom SVG engine and keeps all data local for privacy.https://ramdi.fr/github-stars/navigating-the-ai-agent-ecosystem-with-the-awesome-ai-agents-2026-catalog/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/navigating-the-ai-agent-ecosystem-with-the-awesome-ai-agents-2026-catalog/A living catalog of 340+ AI agent tools and frameworks in 2026, with a deep dive into GNAP’s minimal multi-agent coordination approach using git and JSON files.https://ramdi.fr/github-stars/navigating-the-fragmented-ai-agent-landscape-with-the-awesome-ai-agents-curated-directory/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/navigating-the-fragmented-ai-agent-landscape-with-the-awesome-ai-agents-curated-directory/Explore a curated directory of 1,500+ AI agent tools, frameworks, and projects organized by use case. Essential for developers navigating the rapidly evolving AI agent space.https://ramdi.fr/github-stars/nvidia-nemo-agent-toolkit-enhancing-multi-agent-workflows-with-performance-primitives-and-observability/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/nvidia-nemo-agent-toolkit-enhancing-multi-agent-workflows-with-performance-primitives-and-observability/NVIDIA NeMo Agent Toolkit adds performance primitives, profiling, and runtime intelligence to multi-agent workflows alongside existing frameworks like LangChain. It enables latency-aware routing, token-level profiling, and YAML-driven flows.https://ramdi.fr/github-stars/openclaw-dashboard-a-lightweight-go-server-for-ai-data-visualization-and-interaction/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/openclaw-dashboard-a-lightweight-go-server-for-ai-data-visualization-and-interaction/OpenClaw Dashboard is a Go-based self-hosted web UI for visualizing and interacting with OpenClaw AI data. It offers easy setup, live data refresh, and a chat panel integrated with OpenClaw gateway.https://ramdi.fr/github-stars/openmythos-exploring-recurrent-depth-transformers-with-input-injection-for-sustained-reasoning/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/openmythos-exploring-recurrent-depth-transformers-with-input-injection-for-sustained-reasoning/OpenMythos implements a recurrent-depth transformer that recycles layers via looped blocks, using input injection to prevent signal drift. It scales from 1B to 1T parameters with up to 1M token context.https://ramdi.fr/github-stars/ordinary-claude-skills-an-extensive-local-first-library-of-claude-prompt-packages-for-specialized-ai-agents/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/ordinary-claude-skills-an-extensive-local-first-library-of-claude-prompt-packages-for-specialized-ai-agents/Discover ordinary-claude-skills, a local-first collection of 600+ prompt packages that specialize Claude AI with domain skills, integrated via MCP filesystem for lazy loading.https://ramdi.fr/github-stars/restai-a-multi-project-aiaas-platform-with-agentic-browser-automation-and-visual-ai-pipelines/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/restai-a-multi-project-aiaas-platform-with-agentic-browser-automation-and-visual-ai-pipelines/RESTai exposes multi-project AI capabilities via a unified REST API, featuring an agentic browser with Dockerized Playwright, knowledge graph RAG, and a visual Blockly pipeline builder.https://ramdi.fr/github-stars/spec-first-web-design-with-claude-code-enforcing-design-contracts-via-design-md/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/spec-first-web-design-with-claude-code-enforcing-design-contracts-via-design-md/web-design is a Claude Code SKILL that enforces a spec-first web design workflow via DESIGN.md, bridging AI code generation with consistent, testable design output.https://ramdi.fr/github-stars/standardizing-ai-agent-capabilities-with-modular-skill-files-in-yofine-skills/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/standardizing-ai-agent-capabilities-with-modular-skill-files-in-yofine-skills/yofine/skills offers a minimal, modular approach to AI agent capabilities with SKILL.md files using YAML frontmatter, exemplified by a technical diagram skill generating Flat Engineering Blueprints.https://ramdi.fr/github-stars/standardizing-ai-agent-workflows-with-agent-sops-and-markdown-driven-constraints/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/standardizing-ai-agent-workflows-with-agent-sops-and-markdown-driven-constraints/Agent SOPs offers a Python SDK that defines AI agent workflows as markdown-based SOPs with RFC 2119 constraints, solving reproducibility and artifact management challenges.https://ramdi.fr/github-stars/whyhow-knowledge-graph-studio-building-rag-native-knowledge-graphs-with-mongodb-and-openai/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/whyhow-knowledge-graph-studio-building-rag-native-knowledge-graphs-with-mongodb-and-openai/WhyHow Knowledge Graph Studio builds RAG-native knowledge graphs using MongoDB and OpenAI embeddings, offering flexible triple-based graph construction for AI workflows.https://ramdi.fr/github-stars/xplorer-a-modern-ai-native-file-manager-built-with-tauri-rust-and-react/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/xplorer-a-modern-ai-native-file-manager-built-with-tauri-rust-and-react/Xplorer is a Tauri-based desktop file manager integrating AI for semantic search, context-aware chat, and agentic file ops. Built with Rust backend and React frontend.https://ramdi.fr/github-stars/blueprint-mcp-async-ai-diagram-generation-for-code-architecture-visualization/Mon, 04 May 2026 10:17:20 +0000https://ramdi.fr/github-stars/blueprint-mcp-async-ai-diagram-generation-for-code-architecture-visualization/Blueprint MCP is a Python MCP server that generates system diagrams from codebases asynchronously using Google’s Nano Banana Pro model, integrated with Arcade MCP and Cursor IDE.https://ramdi.fr/github-stars/turning-text-into-ai-podcast-episodes-with-a-coding-agent-and-fish-audio-tts/Mon, 04 May 2026 10:16:09 +0000https://ramdi.fr/github-stars/turning-text-into-ai-podcast-episodes-with-a-coding-agent-and-fish-audio-tts/personalized-podcast turns text or URLs into two-host AI podcast episodes using Claude Code for script writing and Fish Audio TTS for voice synthesis, all in a streamlined pipeline.https://ramdi.fr/github-stars/meridian-tackling-ai-session-context-loss-with-smart-lifecycle-hooks-and-project-scaffolding/Mon, 04 May 2026 10:13:55 +0000https://ramdi.fr/github-stars/meridian-tackling-ai-session-context-loss-with-smart-lifecycle-hooks-and-project-scaffolding/Meridian is a Claude Code plugin that solves session context loss in long AI coding sessions using lifecycle hooks and a persistent project workspace. Here’s how it works and how to get started.https://ramdi.fr/github-stars/unifying-ai-coding-assistant-rules-with-awesome-rules-and-rules-cli/Mon, 04 May 2026 10:11:28 +0000https://ramdi.fr/github-stars/unifying-ai-coding-assistant-rules-with-awesome-rules-and-rules-cli/awesome-rules standardizes AI coding assistant rules with markdown+YAML and translates formats via rules-cli, easing multi-assistant compatibility.https://ramdi.fr/github-stars/ai-penetration-testing-knowledge-base-structured-resources-for-llm-security-research/Mon, 04 May 2026 10:09:00 +0000https://ramdi.fr/github-stars/ai-penetration-testing-knowledge-base-structured-resources-for-llm-security-research/A curated repository for AI/LLM penetration testing covering prompt injection, adversarial ML, and LLM red teaming with the OWASP LLM Top 10 framework.https://ramdi.fr/github-stars/agenticailabs-ai-engineering-roadmap-a-modular-curriculum-for-self-taught-ai-engineers/Mon, 04 May 2026 10:08:13 +0000https://ramdi.fr/github-stars/agenticailabs-ai-engineering-roadmap-a-modular-curriculum-for-self-taught-ai-engineers/AgenticAiLabs AI Engineering Roadmap offers a modular, community-curated curriculum for self-taught AI engineers, covering from fundamentals to advanced AI topics like LLMs and RAG.https://ramdi.fr/github-stars/navigating-free-tier-llm-apis-with-the-awesome-free-llm-apis-catalog/Sun, 03 May 2026 08:12:11 +0000https://ramdi.fr/github-stars/navigating-free-tier-llm-apis-with-the-awesome-free-llm-apis-catalog/A curated catalog of free-tier LLM APIs compatible with OpenAI SDK, detailing rate limits, model specs, and providers to build zero-cost AI applications.https://ramdi.fr/github-stars/crewai-a-lean-python-framework-for-orchestrating-autonomous-ai-agents-with-precise-control/Sat, 02 May 2026 20:17:54 +0000https://ramdi.fr/github-stars/crewai-a-lean-python-framework-for-orchestrating-autonomous-ai-agents-with-precise-control/CrewAI is a Python framework for autonomous AI agents emphasizing speed, flexibility, and precise control through ‘Crews’ and ‘Flows’. It offers enterprise features for production-grade AI orchestration.https://ramdi.fr/github-stars/agno-building-production-ready-agentic-software-with-minimal-code/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/agno-building-production-ready-agentic-software-with-minimal-code/Agno provides a minimal, production-ready Python framework for scalable agentic software with per-user isolation and native tracing in ~20 lines of code.https://ramdi.fr/github-stars/awesome-go-a-curated-gateway-to-the-go-ecosystem-s-diverse-libraries-and-tools/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/awesome-go-a-curated-gateway-to-the-go-ecosystem-s-diverse-libraries-and-tools/awesome-go is a community-driven curated list of Go frameworks and libraries, highlighting the language’s breadth from core tools to emerging AI projects. Essential for Go developers exploring the ecosystem.https://ramdi.fr/github-stars/bagisto-a-laravel-based-e-commerce-platform-embracing-ai-and-decentralized-commerce/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/bagisto-a-laravel-based-e-commerce-platform-embracing-ai-and-decentralized-commerce/Bagisto is an open-source Laravel and Vue.js e-commerce platform that integrates AI-powered features and blockchain for decentralized commerce. A practical look under the hood.https://ramdi.fr/github-stars/exploring-microsoft-s-generative-ai-for-beginners-a-dual-language-practical-course/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/exploring-microsoft-s-generative-ai-for-beginners-a-dual-language-practical-course/Microsoft’s “Generative AI for Beginners” offers 21 lessons with Python and TypeScript examples covering LLMs, prompt engineering, RAG, and AI app building.https://ramdi.fr/github-stars/hermes-agent-a-self-improving-ai-agent-with-closed-learning-loops-and-multi-platform-integration/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/hermes-agent-a-self-improving-ai-agent-with-closed-learning-loops-and-multi-platform-integration/Hermes Agent is a Python AI agent featuring closed learning loops, autonomous skill creation, multi-model support, and seamless Telegram/Discord integration for persistent, adaptable AI workflows.https://ramdi.fr/github-stars/how-laravel-ai-sdk-simplifies-integrating-multiple-ai-providers-in-php/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/how-laravel-ai-sdk-simplifies-integrating-multiple-ai-providers-in-php/Laravel AI SDK offers a unified API to integrate OpenAI, Anthropic, Gemini, and more, streamlining AI workflows in Laravel apps with minimal boilerplate.https://ramdi.fr/github-stars/javaguide-a-comprehensive-backend-interview-resource-expanding-into-ai-application-development/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/javaguide-a-comprehensive-backend-interview-resource-expanding-into-ai-application-development/JavaGuide offers a thorough Java backend interview preparation resource now including AI application development with AI Agents, RAG, and MCP protocol concepts for modern backend roles.https://ramdi.fr/github-stars/langflow-visual-orchestration-platform-for-ai-agents-and-workflows/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/langflow-visual-orchestration-platform-for-ai-agents-and-workflows/Langflow offers a Python-based visual platform to build and deploy AI agents and workflows with multi-agent orchestration, vector DB support, and enterprise features.https://ramdi.fr/github-stars/localai-running-diverse-ai-models-locally-with-multi-backend-support-and-agent-capabilities/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/localai-running-diverse-ai-models-locally-with-multi-backend-support-and-agent-capabilities/LocalAI enables running 36+ AI models locally without GPU, supporting multi-user API access and built-in AI agents with OpenAI-compatible APIs. Here’s how it works and why it matters.https://ramdi.fr/github-stars/mem0-optimizing-ai-agent-memory-with-a-new-single-pass-additive-algorithm/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/mem0-optimizing-ai-agent-memory-with-a-new-single-pass-additive-algorithm/mem0 enhances AI agent memory with a new single-pass ADD-only extraction algorithm and multi-signal retrieval, boosting benchmarks significantly while simplifying memory management.https://ramdi.fr/github-stars/photoprism-ai-powered-privacy-first-photo-management-for-self-hosted-environments/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/photoprism-ai-powered-privacy-first-photo-management-for-self-hosted-environments/PhotoPrism offers AI-driven photo management with facial recognition and tagging in a self-hosted, privacy-focused platform. Explore its architecture, tech, and tradeoffs.https://ramdi.fr/github-stars/symfony-ai-unified-ai-integration-for-php-applications-with-symfony/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/symfony-ai-unified-ai-integration-for-php-applications-with-symfony/Symfony AI unifies multiple AI platforms into a single PHP interface, enabling flexible AI-powered Symfony apps without vendor lock-in. It includes AI agents, chat context, and data indexing components.https://ramdi.fr/github-stars/trendradar-ai-powered-multi-platform-trend-monitoring-with-mcp-architecture/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/trendradar-ai-powered-multi-platform-trend-monitoring-with-mcp-architecture/TrendRadar is a self-hosted AI-driven tool for multi-platform trend monitoring, using MCP architecture for advanced language analysis and smart push notifications across popular messaging platforms.https://ramdi.fr/post/ai-llm/local-llm-tokens-per-second-benchmark/Tue, 28 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/local-llm-tokens-per-second-benchmark/Part 2 of 4: a benchmark journal across nixpkgs llama.cpp, upstream master, and ik_llama.cpp on Qwen3.6-27B. Six hours, four backends, all converging at 66 tok/s — and the physical reason why.https://ramdi.fr/post/ai-llm/local-llm-speculative-decoding-hybrid-ssm/Tue, 28 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/local-llm-speculative-decoding-hybrid-ssm/Part 3 of 4: a deep-dive into why speculative decoding silently breaks (or runs anti-economically) on hybrid attention+SSM architectures like Qwen3.6, Mamba-2, and RWKV — and what would need to change upstream to fix it.https://ramdi.fr/post/ai-llm/local-llm-nixos-llama-server-module/Tue, 28 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/local-llm-nixos-llama-server-module/Part 4 of 4: the actual NixOS module, llama-pull helper, claude-code-router wiring, and one-line workflow for switching models. Five Nix files for a complete, isolated, rollback-able local LLM service.https://ramdi.fr/post/ai-llm/local-llm-rtx5090-why-nixos/Tue, 28 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/local-llm-rtx5090-why-nixos/Part 1 of 4: motivation, hardware, and stack choices for serving Qwen3.6-27B locally on a 32 GB consumer GPU with NixOS, before any benchmarks or trade-offs kick in.https://ramdi.fr/github-stars/cc-switch-unified-management-for-ai-coding-clis-in-a-cross-platform-rust-desktop-app/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/cc-switch-unified-management-for-ai-coding-clis-in-a-cross-platform-rust-desktop-app/CC Switch is a Rust-based cross-platform desktop app that centralizes management of AI coding CLIs like Claude Code and Codex. It streamlines switching providers, prompt templating, and session persistence.https://ramdi.fr/github-stars/inside-ai-engineering-hub-a-hands-on-collection-of-production-ready-ai-projects/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/inside-ai-engineering-hub-a-hands-on-collection-of-production-ready-ai-projects/AI Engineering Hub offers 90+ production-ready AI projects spanning LLMs, RAG, AI agents, and MCP, organized by difficulty and real-world use cases.https://ramdi.fr/github-stars/kong-gateway-a-universal-api-gateway-with-advanced-ai-traffic-routing-and-governance/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/kong-gateway-a-universal-api-gateway-with-advanced-ai-traffic-routing-and-governance/Kong Gateway extends traditional API management with universal LLM API routing, semantic security, and AI-specific features, enabling multi-vendor AI traffic governance in cloud-native environments.https://ramdi.fr/github-stars/openhands-modular-architecture-for-flexible-ai-agent-development/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/openhands-modular-architecture-for-flexible-ai-agent-development/OpenHands offers a modular Python platform to build and deploy AI agents with SDK, CLI, GUI, and cloud options. It supports multiple LLMs and self-hosting for enterprises.https://ramdi.fr/github-stars/hugging-face-transformers-a-unified-api-for-state-of-the-art-ai-models-across-modalities/Sun, 26 Apr 2026 09:31:26 +0000https://ramdi.fr/github-stars/hugging-face-transformers-a-unified-api-for-state-of-the-art-ai-models-across-modalities/Hugging Face Transformers offers a unified Python API to access over 1 million pretrained AI models for text, vision, and audio, simplifying complex pipelines with its Pipeline API.https://ramdi.fr/github-stars/openai-skills-modular-agent-skills-for-reusable-ai-capabilities/Sat, 25 Apr 2026 07:57:59 +0000https://ramdi.fr/github-stars/openai-skills-modular-agent-skills-for-reusable-ai-capabilities/The openai/skills repo offers a catalog of modular ‘Agent Skills’ for OpenAI Codex agents, enabling reusable AI functionalities with a standardized installation system.https://ramdi.fr/github-stars/cloudflare-agents-building-persistent-ai-agents-with-stateful-durable-objects/Fri, 24 Apr 2026 07:26:29 +0000https://ramdi.fr/github-stars/cloudflare-agents-building-persistent-ai-agents-with-stateful-durable-objects/Cloudflare Agents offers a TypeScript framework for stateful AI agents on Durable Objects with real-time communication, AI integration, and sandboxed code execution.https://ramdi.fr/github-stars/openai-codex-cli-local-first-ai-coding-assistant-with-chatgpt-integration/Thu, 23 Apr 2026 23:28:46 +0000https://ramdi.fr/github-stars/openai-codex-cli-local-first-ai-coding-assistant-with-chatgpt-integration/OpenAI Codex CLI brings AI coding assistance local to your terminal, integrating with ChatGPT plans for powerful hybrid AI workflows. Here’s how it works and who it’s for.https://ramdi.fr/post/ai-llm/building-ai-agents-with-claude/Sat, 11 Apr 2026 00:00:00 +0000https://ramdi.fr/post/ai-llm/building-ai-agents-with-claude/How to leverage Claude Code to build autonomous AI agents that publish content, review code, and manage workflows.