https://ramdi.fr/tags/ai-agents/Recent content in Ai-Agents on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000https://ramdi.fr/github-stars/agentflow-orchestrating-ai-coding-agents-with-programmatic-dependency-graphs/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/agentflow-orchestrating-ai-coding-agents-with-programmatic-dependency-graphs/AgentFlow uses Python’s graph-based DSL to orchestrate AI coding agents with parallelism, iteration, and remote execution. It supports Codex, Claude, and others.https://ramdi.fr/github-stars/autoskill-experience-driven-lifelong-learning-for-llm-agents-with-skill-versioning-and-evolution/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/autoskill-experience-driven-lifelong-learning-for-llm-agents-with-skill-versioning-and-evolution/AutoSkill is a Python framework enabling LLM agents to extract, version, and evolve skills from dialogues, providing a persistent long-term memory system for AI agents.https://ramdi.fr/github-stars/clawd-on-desk-an-ambient-desktop-pet-for-real-time-ai-agent-observability/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/clawd-on-desk-an-ambient-desktop-pet-for-real-time-ai-agent-observability/Clawd on Desk uses an Electron-based desktop pet with pixel-art animations to visualize AI coding agents’ activity in real time, enabling glanceable observability and inline permission handling.https://ramdi.fr/github-stars/clawmetry-zero-config-real-time-observability-dashboard-for-openclaw-ai-agents/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/clawmetry-zero-config-real-time-observability-dashboard-for-openclaw-ai-agents/ClawMetry offers a zero-configuration real-time dashboard for OpenClaw AI agents, visualizing message flows, token usage, and operational alerts with easy setup.https://ramdi.fr/github-stars/clay-a-self-hosted-multiplayer-ai-workspace-with-persistent-ai-teammates-and-autonomous-coding-loops/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/clay-a-self-hosted-multiplayer-ai-workspace-with-persistent-ai-teammates-and-autonomous-coding-loops/Clay unifies local repos into a browser-based dashboard with persistent AI teammates that remember across sessions and iterate autonomously via overnight coding loops. Self-hosted with no cloud lock-in.https://ramdi.fr/github-stars/homeassistant-ai-skills-standardizing-home-assistant-skills-for-ai-coding-agents/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/homeassistant-ai-skills-standardizing-home-assistant-skills-for-ai-coding-agents/homeassistant-ai/skills provides a modular collection of Home Assistant skills for AI coding agents supporting the Agent Skills standard, easing integration with tools like Claude Code and Copilot.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-opencode-power-pack-bridges-claude-code-workflows-into-opencode/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/how-opencode-power-pack-bridges-claude-code-workflows-into-opencode/opencode-power-pack translates Anthropic’s Claude Code plugins into OpenCode SKILL.md files, enabling multi-agent AI coding workflows across platforms. Here’s how it works under the hood.https://ramdi.fr/github-stars/inside-gtm-agents-a-claude-code-marketplace-for-specialized-gtm-ai-plugins/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/inside-gtm-agents-a-claude-code-marketplace-for-specialized-gtm-ai-plugins/gtm-agents bundles 67 GTM plugins, 92 AI agents, 52 business skills, and 20 workflow orchestrators for Claude Code, saving 15+ hours/week on sales and marketing busywork.https://ramdi.fr/github-stars/inside-red-run-ai-agent-orchestration-for-offensive-security-assessments/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/inside-red-run-ai-agent-orchestration-for-offensive-security-assessments/red-run orchestrates Claude Code AI agent teams across the full pentest kill chain using persistent teammates and semantic routing. Explore its architecture, strengths, and quickstart.https://ramdi.fr/github-stars/integrating-google-workspace-with-ai-agents-via-the-google-docs-mcp-server/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/integrating-google-workspace-with-ai-agents-via-the-google-docs-mcp-server/The google-docs-mcp server exposes Google Docs, Sheets, Drive, Gmail, and Calendar as callable tools for AI agents like Claude Desktop, enabling deep document and email automation via OAuth2.https://ramdi.fr/github-stars/llm4pentest-a-curated-knowledge-hub-on-large-language-models-for-automated-penetration-testing/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/llm4pentest-a-curated-knowledge-hub-on-large-language-models-for-automated-penetration-testing/LLM4Pentest aggregates 40+ research papers and tools tracking the evolving role of LLMs in automated penetration testing, highlighting progress and limitations.https://ramdi.fr/github-stars/mcp-selenium-structured-browser-automation-for-ai-agents-via-mcp/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/mcp-selenium-structured-browser-automation-for-ai-agents-via-mcp/mcp-selenium exposes Selenium WebDriver as typed MCP tools for AI agents, supporting multi-browser automation with WebDriver BiDi diagnostics. Setup is easy with npx commands.https://ramdi.fr/github-stars/native-devtools-mcp-cross-platform-ai-agent-control-of-native-apps-with-macos-accessibility-precision/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/native-devtools-mcp-cross-platform-ai-agent-control-of-native-apps-with-macos-accessibility-precision/native-devtools-mcp provides a Rust-based MCP server letting AI agents control native desktop apps on macOS/Windows, Chrome/Electron browsers, and Android devices. It features macOS AX dispatch for precise, focus-free app control.https://ramdi.fr/github-stars/opcode-a-tauri-desktop-app-turning-claude-code-cli-into-a-graphical-ai-developer-cockpit/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/opcode-a-tauri-desktop-app-turning-claude-code-cli-into-a-graphical-ai-developer-cockpit/opcode is a cross-platform Tauri desktop app that wraps Claude Code CLI with a GUI, session checkpointing, custom AI agents, MCP server management, and usage analytics.https://ramdi.fr/github-stars/openclaw-agents-orchestrating-adversarial-ai-agents-with-shell-driven-provisioning/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/openclaw-agents-orchestrating-adversarial-ai-agents-with-shell-driven-provisioning/OpenClaw Agents deploys paired AI agents using shell scripts for adversarial collaboration in OpenClaw gateway, supporting multi-channel or local workflows with safe config merges.https://ramdi.fr/github-stars/openui-a-visual-canvas-for-managing-multiple-ai-agents-with-real-time-status-and-session-persistence/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/openui-a-visual-canvas-for-managing-multiple-ai-agents-with-real-time-status-and-session-persistence/OpenUI provides a TypeScript CLI and browser UI to spawn, organize, and monitor multiple AI agents with session persistence and real-time status. Easy to start and extend.https://ramdi.fr/github-stars/ori-mnemos-scoped-memory-management-for-ai-agents-in-typescript/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/ori-mnemos-scoped-memory-management-for-ai-agents-in-typescript/Ori-Mnemos provides a TypeScript CLI tool for managing AI agent memory with scoped vaults and activation modes, enabling persistent and flexible context handling.https://ramdi.fr/github-stars/scenesmith-ai-driven-pipeline-for-physics-ready-3d-indoor-scene-generation-from-text/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/scenesmith-ai-driven-pipeline-for-physics-ready-3d-indoor-scene-generation-from-text/SceneSmith uses GPT-5-powered agents to generate physically plausible 3D indoor scenes from text prompts, ready for robotics simulation without manual cleanup.https://ramdi.fr/github-stars/ultimate-ai-engineer-roadmap-2026-a-comprehensive-curriculum-for-aspiring-ai-engineers/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/ultimate-ai-engineer-roadmap-2026-a-comprehensive-curriculum-for-aspiring-ai-engineers/Explore a detailed 17-phase AI engineering roadmap for 2026, focusing on multi-LLM orchestration, RAG, AI agents, and production-ready skills with 51 hands-on projects.https://ramdi.fr/github-stars/world2agent-standardizing-ai-agent-perception-with-pluggable-npm-sensors/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/world2agent-standardizing-ai-agent-perception-with-pluggable-npm-sensors/World2Agent defines a TypeScript protocol for AI agents to ingest real-world data as pluggable npm sensors, with runtime bridges for Claude Code, Hermes, and OpenClaw.https://ramdi.fr/github-stars/xcodebuildmcp-bridging-ai-agents-and-native-apple-development-with-mcp-tools/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/xcodebuildmcp-bridging-ai-agents-and-native-apple-development-with-mcp-tools/XcodeBuildMCP exposes xcodebuild operations as MCP tools for AI coding assistants and CLI use, enabling automated iOS/macOS builds, testing, and debugging with a per-workspace daemon on macOS.https://ramdi.fr/github-stars/openshell-securing-ai-agents-with-runtime-policy-sandboxing-from-nvidia/Mon, 18 May 2026 18:25:17 +0000https://ramdi.fr/github-stars/openshell-securing-ai-agents-with-runtime-policy-sandboxing-from-nvidia/OpenShell by NVIDIA offers a Rust-based AI agent sandbox runtime with hot-reloadable YAML policies for filesystem, network, process, and inference controls inside containers.https://ramdi.fr/github-stars/openalpha-evolve-autonomous-code-evolution-with-llm-driven-diff-mutations/Sat, 09 May 2026 11:42:26 +0000https://ramdi.fr/github-stars/openalpha-evolve-autonomous-code-evolution-with-llm-driven-diff-mutations/OpenAlpha_Evolve uses large language models to generate precise code diffs as mutations in an evolutionary algorithm, enabling autonomous iterative code improvement with sandboxed evaluation.https://ramdi.fr/github-stars/hash-autonomous-ai-driven-knowledge-graph-platform-with-rust-and-multi-service-architecture/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/hash-autonomous-ai-driven-knowledge-graph-platform-with-rust-and-multi-service-architecture/HASH is a Rust-based multi-tenant knowledge graph platform using autonomous AI agents to build and validate data. It combines Rust backend, TypeScript workers, and Docker services with LLM integrations.https://ramdi.fr/github-stars/octopoda-os-a-memory-layer-for-ai-agents-with-loop-detection-and-audit-trails/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/octopoda-os-a-memory-layer-for-ai-agents-with-loop-detection-and-audit-trails/Octopoda-OS is a Python library providing persistent memory, loop detection, and audit trails for AI agents. It supports SQLite/PostgreSQL, zero-config runtime, and cloud sync.https://ramdi.fr/github-stars/tinyagi-a-lightweight-multi-agent-orchestration-platform-with-sqlite-backed-task-queue/Tue, 05 May 2026 16:46:42 +0000https://ramdi.fr/github-stars/tinyagi-a-lightweight-multi-agent-orchestration-platform-with-sqlite-backed-task-queue/TinyAGI is a TypeScript platform for solo operators managing multiple AI agent teams. It uses a SQLite queue with atomic transactions for reliable async task processing and supports multi-channel messaging.https://ramdi.fr/github-stars/agentic-stack-portable-multi-agent-memory-for-ai-coding-assistants/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/agentic-stack-portable-multi-agent-memory-for-ai-coding-assistants/agentic-stack provides a harness-agnostic shared memory layer for AI coding agents, enabling seamless context persistence and migration across tools like Claude Code and Cursor.https://ramdi.fr/github-stars/nanobrowser-multi-agent-ai-browser-automation-with-dynamic-self-correcting-planning/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/nanobrowser-multi-agent-ai-browser-automation-with-dynamic-self-correcting-planning/Nanobrowser is a TypeScript Chrome extension implementing a multi-agent AI system for browser automation with a unique self-correcting Planner-Navigator architecture, supporting multiple LLMs and local privacy.https://ramdi.fr/github-stars/site-md-next-js-middleware-serving-markdown-to-ai-agents-without-content-duplication/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/site-md-next-js-middleware-serving-markdown-to-ai-agents-without-content-duplication/site-md uses Next.js middleware to serve clean Markdown to AI agents and HTML to humans, converting HTML on-the-fly without duplicating content. Easy install with minimal setup.https://ramdi.fr/github-stars/zenml-a-unified-mlops-platform-bridging-classical-ml-and-ai-agent-orchestration/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/zenml-a-unified-mlops-platform-bridging-classical-ml-and-ai-agent-orchestration/ZenML offers an open-source Python SDK to orchestrate full ML and AI agent lifecycles, integrating popular tools and enabling natural-language MLOps interactions via its MCP server.https://ramdi.fr/github-stars/awesome-sandbox-comparing-modern-sandboxing-tech-for-ai-agent-execution/Mon, 04 May 2026 10:23:03 +0000https://ramdi.fr/github-stars/awesome-sandbox-comparing-modern-sandboxing-tech-for-ai-agent-execution/A curated repo comparing sandboxing technologies for secure, fast AI agent execution. Covers microVMs, containers, WebAssembly, and more with tradeoffs on security vs speed.https://ramdi.fr/github-stars/evoclaw-structured-memory-and-identity-evolution-framework-for-openclaw-ai-agents/Mon, 04 May 2026 10:23:03 +0000https://ramdi.fr/github-stars/evoclaw-structured-memory-and-identity-evolution-framework-for-openclaw-ai-agents/EvoClaw enforces AI agent memory and identity evolution with an 8-validator pipeline ensuring integrity and governance, featuring a tiered memory system and radial mindmap UI.https://ramdi.fr/github-stars/agent-sat-autonomous-ai-agent-discovering-maxsat-solving-techniques-through-iterative-experimentation/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/agent-sat-autonomous-ai-agent-discovering-maxsat-solving-techniques-through-iterative-experimentation/agent-sat is an autonomous AI agent system where Claude Code learns to solve weighted MaxSAT problems by iterating solver improvements and coordinating via git, solving 220/229 benchmarks.https://ramdi.fr/github-stars/agentflow-orchestrating-ai-coding-agents-with-graph-based-parallelism-and-remote-execution/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/agentflow-orchestrating-ai-coding-agents-with-graph-based-parallelism-and-remote-execution/AgentFlow is a Python library for orchestrating AI coding agents using dependency graphs, supporting parallel fanout, iterative refinement, and remote execution. It integrates with Codex CLI for natural-language pipeline creation.https://ramdi.fr/github-stars/agentic-coding-flywheel-setup-bootstrapping-ai-powered-coding-agents-on-a-vps/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/agentic-coding-flywheel-setup-bootstrapping-ai-powered-coding-agents-on-a-vps/Agentic Coding Flywheel Setup automates turning a fresh Ubuntu VPS into an AI-powered coding environment with autonomous agents, simplifying complex setups into a single command.https://ramdi.fr/github-stars/agentops-a-local-operating-layer-for-cross-vendor-ai-coding-agents-with-multi-agent-consensus/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/agentops-a-local-operating-layer-for-cross-vendor-ai-coding-agents-with-multi-agent-consensus/AgentOps provides a Go-based local operating layer for AI coding agents, enabling persistent memory, validation gates, and multi-agent review across vendors with zero cloud dependency.https://ramdi.fr/github-stars/agentsmesh-a-self-hosted-ai-agent-orchestration-platform-with-control-plane-data-plane-separation/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/agentsmesh-a-self-hosted-ai-agent-orchestration-platform-with-control-plane-data-plane-separation/AgentsMesh offers a self-hosted AI agent orchestration platform with a clean control/data plane split using gRPC+mTLS and WebSocket relay for real-time terminal I/O streaming.https://ramdi.fr/github-stars/autoprober-ai-driven-hardware-automation-with-oscilloscope-monitored-safety-for-pcb-analysis/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/autoprober-ai-driven-hardware-automation-with-oscilloscope-monitored-safety-for-pcb-analysis/AutoProber is a Python automation stack that controls a flying probe system for PCB analysis, featuring oscilloscope-based safety monitoring and a Flask dashboard.https://ramdi.fr/github-stars/cass-memory-a-typescript-cognitive-memory-system-with-confidence-decay-for-ai-coding-agents/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/cass-memory-a-typescript-cognitive-memory-system-with-confidence-decay-for-ai-coding-agents/cass-memory is a TypeScript CLI implementing a three-layer cognitive architecture for AI coding agents, featuring a novel confidence decay system to maintain a reliable, evolving knowledge base.https://ramdi.fr/github-stars/claude-code-viewer-a-pragmatic-web-ui-for-managing-claude-code-agent-sessions/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/claude-code-viewer-a-pragmatic-web-ui-for-managing-claude-code-agent-sessions/Claude Code Viewer provides a web UI for real-time monitoring and managing Claude Code sessions with dual authentication modes and PWA mobile support. It handles Anthropic’s SDK restrictions gracefully.https://ramdi.fr/github-stars/claude-code-harness-a-shell-based-plugin-harness-for-claude-code-ai-agents/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/claude-code-harness-a-shell-based-plugin-harness-for-claude-code-ai-agents/claude-code-harness is a Shell plugin harness for Claude Code that integrates AI agent features without Node.js, relying on specific Claude Code and Opus versions for full capability.https://ramdi.fr/github-stars/claudemap-visual-interactive-map-for-claude-ai-agents-with-codex-support/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/claudemap-visual-interactive-map-for-claude-ai-agents-with-codex-support/claudemap offers a JavaScript runtime to create and run visual interactive maps for Claude AI agents, with optional Codex assistant integration for enhanced natural language control.https://ramdi.fr/github-stars/ctx-managing-ai-skills-and-agents-with-a-context-aware-knowledge-graph/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/ctx-managing-ai-skills-and-agents-with-a-context-aware-knowledge-graph/ctx builds a 104K-node knowledge graph to optimize AI skill and agent selection for Claude Code, solving context window bloat with a graph-based recommender and lifecycle management.https://ramdi.fr/github-stars/extending-vercel-ai-sdk-with-modular-typescript-tools-for-ai-applications/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/extending-vercel-ai-sdk-with-modular-typescript-tools-for-ai-applications/ai-sdk-tools offers modular TypeScript packages extending Vercel AI SDK with production-ready patterns like multi-agent orchestration and type-safe streaming artifacts for React apps.https://ramdi.fr/github-stars/goose-skills-modular-gtm-ai-agent-skills-for-sales-and-marketing-automation/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/goose-skills-modular-gtm-ai-agent-skills-for-sales-and-marketing-automation/Goose Skills provides 108 reusable AI agent skills for sales, marketing, and competitive intelligence, structured as atomic tools, skill chains, and workflows for coding agents like Claude and Codex.https://ramdi.fr/github-stars/kitaru-a-durable-runtime-for-autonomous-ai-agents-with-checkpointed-execution/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/kitaru-a-durable-runtime-for-autonomous-ai-agents-with-checkpointed-execution/Kitaru offers a framework-agnostic runtime for autonomous AI agents with durable execution via checkpointing, enabling replay and state preservation to avoid costly restarts on failures.https://ramdi.fr/github-stars/kohakuterrarium-modular-ai-agent-composition-with-algebraic-pipelines/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/kohakuterrarium-modular-ai-agent-composition-with-algebraic-pipelines/KohakuTerrarium offers a Python framework to build modular AI agents using a unique algebra for composing multi-agent pipelines, with session persistence and multi-runtime support.https://ramdi.fr/github-stars/mapping-the-llm-agent-landscape-with-the-awesome-llm-agents-curated-catalog/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/mapping-the-llm-agent-landscape-with-the-awesome-llm-agents-curated-catalog/A curated catalog of 20+ LLM agent frameworks and tools organized by agent type and capabilities. Understand architectural differences and trade-offs in LLM agent design.https://ramdi.fr/github-stars/octogent-a-local-orchestration-layer-for-multi-agent-workflows-with-claude-code/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/octogent-a-local-orchestration-layer-for-multi-agent-workflows-with-claude-code/Octogent adds a local orchestration layer on Claude Code for multi-agent workflows using ’tentacles’ — scoped context directories that isolate work and enable inter-agent messaging.https://ramdi.fr/github-stars/open-computer-use-orchestrating-multi-agent-ai-for-real-computer-control-with-containerized-vms/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/open-computer-use-orchestrating-multi-agent-ai-for-real-computer-control-with-containerized-vms/Open Computer Use enables AI agents to control real computers using specialized Browser, Terminal, and Desktop agents running in isolated Docker VMs. It achieves 82% on the OSWorld benchmark.https://ramdi.fr/github-stars/openclaw-client-a-self-hosted-multi-agent-ai-chat-interface-with-streaming-thinking-separation/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/openclaw-client-a-self-hosted-multi-agent-ai-chat-interface-with-streaming-thinking-separation/OpenClaw Client offers a self-hosted web UI to manage OpenClaw AI agents with streaming response separation, file uploads to agent workspaces, JWT auth, and PWA install.https://ramdi.fr/github-stars/packaging-product-management-expertise-as-claude-code-skills-with-lenny-skills/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/packaging-product-management-expertise-as-claude-code-skills-with-lenny-skills/lenny-skills packages product management knowledge as markdown skills for Claude Code, enabling AI agents to apply frameworks from top product leaders. Install via npx skills CLI.https://ramdi.fr/github-stars/scientific-agent-skills-modular-ai-capabilities-for-complex-scientific-workflows/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/scientific-agent-skills-modular-ai-capabilities-for-complex-scientific-workflows/Scientific Agent Skills extends AI coding agents with 135 domain-specific scientific skills, unifying database queries and multi-step workflows across bioinformatics, chemistry, and clinical research.https://ramdi.fr/github-stars/smux-a-shell-driven-multi-agent-communication-layer-using-tmux-panes/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/smux-a-shell-driven-multi-agent-communication-layer-using-tmux-panes/smux leverages tmux panes and a CLI bridge to enable AI agents to collaborate inside the terminal without APIs or shared state. Simple install, macOS/Linux compatible.https://ramdi.fr/github-stars/souls-directory-a-curated-next-js-directory-for-soul-md-ai-agent-personalities/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/souls-directory-a-curated-next-js-directory-for-soul-md-ai-agent-personalities/souls-directory is a Next.js app hosting curated SOUL.md personality templates for OpenClaw AI agents, using Convex backend and GitHub OAuth. Explore its architecture and usage.https://ramdi.fr/github-stars/text-to-cad-ai-driven-parametric-cad-with-geometry-aware-iterative-editing/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/text-to-cad-ai-driven-parametric-cad-with-geometry-aware-iterative-editing/text-to-cad bridges AI coding agents with parametric CAD using a local-first architecture and a novel @cad reference system for geometry-aware iterative edits and multi-format export.https://ramdi.fr/github-stars/tolaria-a-tauri-desktop-app-for-managing-markdown-knowledge-bases-with-ai-agent-integration/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/tolaria-a-tauri-desktop-app-for-managing-markdown-knowledge-bases-with-ai-agent-integration/Tolaria is a Tauri desktop app for managing markdown knowledge bases with git versioning and AI agent integration via a bundled MCP server. Supports 10,000+ notes offline.https://ramdi.fr/github-stars/tui-use-synchronizing-ai-agents-with-interactive-terminal-programs-through-pty-event-streams/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/tui-use-synchronizing-ai-agents-with-interactive-terminal-programs-through-pty-event-streams/tui-use bridges AI agents and terminal apps by intercepting PTY output with a headless xterm emulator, enabling smart wait semantics for reliable interaction in CLI TUIs.https://ramdi.fr/github-stars/usecomputer-a-native-cross-platform-cli-for-ai-driven-desktop-automation-with-precise-coordinate-mapping/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/usecomputer-a-native-cross-platform-cli-for-ai-driven-desktop-automation-with-precise-coordinate-mapping/usecomputer is a Zig-based native CLI for cross-platform desktop automation, solving coordinate mismatches via a coord-map system for AI agents working with downscaled screenshots.https://ramdi.fr/github-stars/adaptive-video-perception-for-ai-agents-with-claude-video-vision/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/adaptive-video-perception-for-ai-agents-with-claude-video-vision/claude-video-vision adds adaptive video frame extraction and audio transcription to Claude Code, bridging natural language queries with dynamic ffmpeg processing. It supports multiple audio backends and runs on Node.js 20+.https://ramdi.fr/github-stars/clawd-cursor-unified-cross-platform-desktop-control-for-ai-agents/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/clawd-cursor-unified-cross-platform-desktop-control-for-ai-agents/Clawd Cursor offers AI agents native desktop control on Windows, macOS, and Linux with a unified PlatformAdapter and local-first architecture, enabling secure, model-agnostic automation without cloud round-trips.https://ramdi.fr/github-stars/coral-orchestrating-autonomous-ai-coding-agents-with-git-worktree-isolation-and-shared-state/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/coral-orchestrating-autonomous-ai-coding-agents-with-git-worktree-isolation-and-shared-state/CORAL uses git worktree branches combined with symlinked shared state to orchestrate multiple AI coding agents collaborating in real-time. This Python infrastructure supports iterative code improvement through evaluation loops.https://ramdi.fr/github-stars/deepchat-a-unified-electron-desktop-platform-for-multi-llm-ai-agents-with-acp-integration/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/deepchat-a-unified-electron-desktop-platform-for-multi-llm-ai-agents-with-acp-integration/DeepChat is an Electron-based TypeScript desktop app unifying multi-LLM chat, MCP protocols, and ACP agent integration with remote control and Skills support.https://ramdi.fr/github-stars/how-awesome-design-skills-structures-ai-driven-design-consistency-with-skill-md-patterns/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/how-awesome-design-skills-structures-ai-driven-design-consistency-with-skill-md-patterns/awesome-design-skills offers a registry of structured design system files that constrain AI UI code generation for consistent, accessible results using TypeUI CLI.https://ramdi.fr/github-stars/inside-ag2-studio-a-practical-ui-for-ai-agent-prototyping-with-fastapi-and-next-js/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/inside-ag2-studio-a-practical-ui-for-ai-agent-prototyping-with-fastapi-and-next-js/AG2 Studio offers a FastAPI + Next.js UI for prototyping multi-agent AI workflows on the AG2 framework. It supports multiple LLMs and skill composition but is a reference, not production-ready.https://ramdi.fr/github-stars/langalpha-ai-agents-using-programmatic-python-execution-for-financial-research/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/langalpha-ai-agents-using-programmatic-python-execution-for-financial-research/LangAlpha uses AI agents that write and execute Python to analyze financial data, reducing token waste and enabling persistent, steerable multi-agent research workspaces.https://ramdi.fr/github-stars/lich-skills-structured-ai-coding-assistant-skills-with-engineering-rigor/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/lich-skills-structured-ai-coding-assistant-skills-with-engineering-rigor/lich-skills offers seven domain-specific AI coding assistant skills with a focus on spec-driven development and scientific debugging to improve reliability.https://ramdi.fr/github-stars/lumibot-unified-python-trading-library-with-ai-agent-runtime-for-reproducible-strategy-testing/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/lumibot-unified-python-trading-library-with-ai-agent-runtime-for-reproducible-strategy-testing/Lumibot unifies backtesting and live trading for stocks, options, crypto, and forex with AI agent runtime using DuckDB, supporting multiple brokers and data sources.https://ramdi.fr/github-stars/memkraft-local-first-memory-for-ai-agents-with-empirical-self-improvement/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/memkraft-local-first-memory-for-ai-agents-with-empirical-self-improvement/MemKraft is a zero-dependency local-first memory system storing AI agent knowledge as Markdown, featuring bitemporal tracking, hybrid search, and a prompt self-improvement loop.https://ramdi.fr/github-stars/mind-a-structured-persistent-memory-layer-with-3-tier-context-for-ai-agents/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/mind-a-structured-persistent-memory-layer-with-3-tier-context-for-ai-agents/Mind offers a SQLite-backed persistent memory layer with a 3-tier model for AI agents, solving context decay via checkpoint recovery and semantic search integration.https://ramdi.fr/github-stars/observing-ai-agents-at-scale-with-opsrobot-a-vector-based-telemetry-pipeline-for-openclaw-workflows/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/observing-ai-agents-at-scale-with-opsrobot-a-vector-based-telemetry-pipeline-for-openclaw-workflows/opsrobot-ai/opsrobot offers a full-stack observability platform for AI agents, using Vector pipelines to transform OpenClaw logs into structured data in Apache Doris, enabling detailed multi-agent tracing.https://ramdi.fr/github-stars/prefab-a-python-first-declarative-ui-framework-for-agent-generated-mcp-apps/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/prefab-a-python-first-declarative-ui-framework-for-agent-generated-mcp-apps/Prefab offers a Python DSL for building declarative UI compiled to JSON and rendered via React, designed for MCP apps and AI agent-generated interfaces without frontend JavaScript.https://ramdi.fr/github-stars/specialized-claude-code-agents-as-architectural-consultants/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/specialized-claude-code-agents-as-architectural-consultants/A curated repo of 30+ Claude Code agents focusing on architectural consulting across languages, frameworks, and infrastructure. Guidance-first approach flips typical code-gen agents.https://ramdi.fr/github-stars/standardizing-ai-agent-capabilities-with-sanjay3290-ai-skills/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/standardizing-ai-agent-capabilities-with-sanjay3290-ai-skills/Explore sanjay3290/ai-skills, a portable skill collection implementing the open Agent Skills Standard for cross-platform AI agent extensibility. Supports 40+ agents, 20+ skills, with OAuth security.https://ramdi.fr/github-stars/using-an-mcp-server-to-query-meta-ads-api-for-ai-driven-ad-insights/Mon, 04 May 2026 10:18:38 +0000https://ramdi.fr/github-stars/using-an-mcp-server-to-query-meta-ads-api-for-ai-driven-ad-insights/This Python MCP server wraps Meta’s Facebook Ads API into 20+ tools, letting AI agents query ad data conversationally. Setup is simple with a single server.py and token auth.https://ramdi.fr/github-stars/apify-mcp-server-enabling-autonomous-ai-agent-payments-for-web-automation-tools/Mon, 04 May 2026 10:09:30 +0000https://ramdi.fr/github-stars/apify-mcp-server-enabling-autonomous-ai-agent-payments-for-web-automation-tools/Apify MCP Server exposes 8,000+ web automation tools as MCP tools to AI agents, featuring agentic payments allowing autonomous crypto payments for tool execution. Supports HTTPS and local modes.https://ramdi.fr/github-stars/elizaos-a-typescript-monorepo-for-building-and-deploying-ai-agents/Sat, 02 May 2026 20:52:17 +0000https://ramdi.fr/github-stars/elizaos-a-typescript-monorepo-for-building-and-deploying-ai-agents/Explore elizaOS, a TypeScript monorepo for AI agents with CLI and web UI. Build and deploy agents fast or extend with plugins using Bun and Vite.https://ramdi.fr/github-stars/open-design-repurposing-coding-agent-clis-into-a-modular-local-first-design-engine/Sat, 02 May 2026 20:48:38 +0000https://ramdi.fr/github-stars/open-design-repurposing-coding-agent-clis-into-a-modular-local-first-design-engine/Open Design turns 12 coding-agent CLIs into a deterministic design engine with 31 composable skills and 72+ design systems, running locally with sandboxed previews and multi-format export.https://ramdi.fr/github-stars/lobehub-an-extensible-ai-agent-playground-with-mcp-plugin-architecture/Sat, 02 May 2026 20:15:49 +0000https://ramdi.fr/github-stars/lobehub-an-extensible-ai-agent-playground-with-mcp-plugin-architecture/LobeHub offers a TypeScript-based AI agent platform with a unique MCP plugin system for integrating 10,000+ skills and collaborative multi-agent workflows. Explore its architecture and developer experience.https://ramdi.fr/github-stars/camoufox-a-stealthy-firefox-fork-for-ai-agents-and-web-scraping/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/camoufox-a-stealthy-firefox-fork-for-ai-agents-and-web-scraping/Camoufox is a Firefox fork optimized for AI agents and web scraping with stealth fingerprint injection at the C++ level and Python API support.https://ramdi.fr/github-stars/exploring-the-model-context-protocol-with-awesome-mcp-servers-a-curated-directory-of-mcp-server-implementations/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/exploring-the-model-context-protocol-with-awesome-mcp-servers-a-curated-directory-of-mcp-server-implementations/awesome-mcp-servers is a curated list of Model Context Protocol (MCP) servers enabling AI models to interact securely with resources. This article explores its architecture, strengths, and how to navigate it.https://ramdi.fr/github-stars/flowise-visual-low-code-ai-agent-builder-with-a-modular-typescript-monorepo/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/flowise-visual-low-code-ai-agent-builder-with-a-modular-typescript-monorepo/Flowise offers a visual drag-and-drop low-code platform to build AI agents and LLM apps, with a Node.js backend and React frontend in a modular monorepo. Easy to start via npm or Docker.https://ramdi.fr/github-stars/how-wordpress-mcp-adapter-standardizes-ai-agent-interaction-with-wordpress/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/how-wordpress-mcp-adapter-standardizes-ai-agent-interaction-with-wordpress/The WordPress MCP Adapter converts WordPress’s Abilities API into the Model Context Protocol, enabling AI agents to interact with WordPress seamlessly through standardized tools and prompts.https://ramdi.fr/github-stars/inside-agents-a-granular-multi-agent-orchestration-system-with-plugineval-quality-assurance/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/inside-agents-a-granular-multi-agent-orchestration-system-with-plugineval-quality-assurance/Explore agents, a Python-based multi-agent orchestration repo featuring 184 AI agents, 78 plugins, and a three-layer PluginEval framework for plugin quality assurance.https://ramdi.fr/github-stars/spec-kit-ai-driven-spec-driven-development-with-executable-specifications/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/spec-kit-ai-driven-spec-driven-development-with-executable-specifications/Spec Kit redefines software development by turning specifications into executable artifacts guided by AI agents, offering a CLI-driven, human-in-the-loop workflow for predictable software delivery.https://ramdi.fr/github-stars/beads-a-distributed-graph-issue-tracker-for-multi-agent-ai-workflows/Sun, 26 Apr 2026 23:47:28 +0000https://ramdi.fr/github-stars/beads-a-distributed-graph-issue-tracker-for-multi-agent-ai-workflows/Beads is a Go-based CLI tool that uses Dolt-backed version control to manage AI agent tasks as a dependency-aware graph, solving merge conflicts and context window limits with semantic compaction.https://ramdi.fr/github-stars/autogen-exploring-multi-agent-ai-orchestration-with-python-in-maintenance-mode/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/autogen-exploring-multi-agent-ai-orchestration-with-python-in-maintenance-mode/AutoGen is a Python framework for building multi-agent AI applications with LLM integration, now in maintenance mode with Microsoft Agent Framework as its successor. Learn its architecture, strengths, and how to get started.https://ramdi.fr/github-stars/autogpt-a-modular-platform-for-continuous-ai-agents-and-workflow-automation/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/autogpt-a-modular-platform-for-continuous-ai-agents-and-workflow-automation/AutoGPT is a Python-based platform for building and managing continuous AI agents that automate workflows, featuring a modular architecture, low-code agent creation, and benchmarking tools.https://ramdi.fr/github-stars/awesome-copilot-modular-community-plugins-and-agentic-workflows-for-github-copilot/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/awesome-copilot-modular-community-plugins-and-agentic-workflows-for-github-copilot/awesome-copilot is a community-curated collection of plugins and agents that extend GitHub Copilot with modular, agentic workflows managed through a CLI marketplace.https://ramdi.fr/github-stars/context7-injecting-real-time-version-specific-docs-into-llm-workflows/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/context7-injecting-real-time-version-specific-docs-into-llm-workflows/Context7 tackles LLM hallucinations by injecting up-to-date, version-specific library docs directly into AI coding agents’ context via CLI or MCP server integration.https://ramdi.fr/github-stars/deerflow-2-0-orchestrating-multi-agent-ai-workflows-with-flexible-llm-integration/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/deerflow-2-0-orchestrating-multi-agent-ai-workflows-with-flexible-llm-integration/DeerFlow 2.0 is a Python framework for orchestrating AI sub-agents and memory with support for multiple LLMs and execution sandboxes. It uses a modular config and setup wizard for flexible deployment.https://ramdi.fr/github-stars/mindsdb-unified-ai-powered-sql-querying-and-data-fusion-for-diverse-sources/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/mindsdb-unified-ai-powered-sql-querying-and-data-fusion-for-diverse-sources/MindsDB offers an AI-powered SQL-compatible engine that unifies structured and unstructured data across 200+ sources, enabling semantic search and conversational analytics with AI agents.https://ramdi.fr/github-stars/openbb-s-open-data-platform-unified-financial-data-integration-for-diverse-analytics-and-ai/Sun, 26 Apr 2026 09:31:26 +0000https://ramdi.fr/github-stars/openbb-s-open-data-platform-unified-financial-data-integration-for-diverse-analytics-and-ai/OpenBB’s Open Data Platform offers a unified “connect once, consume everywhere” layer bridging financial data sources with Python, Excel, AI agents, and REST APIs for seamless analytics and AI use.https://ramdi.fr/github-stars/awesome-llm-apps-a-practical-collection-of-runnable-ai-agent-and-rag-templates/Fri, 24 Apr 2026 18:26:13 +0000https://ramdi.fr/github-stars/awesome-llm-apps-a-practical-collection-of-runnable-ai-agent-and-rag-templates/Awesome LLM Apps offers 100+ runnable AI agent and RAG templates for quick LLM app development. It supports multiple providers and advanced multi-agent patterns with minimal setup.https://ramdi.fr/github-stars/pinchtab-token-efficient-chrome-automation-for-ai-agents-with-go/Fri, 24 Apr 2026 07:26:29 +0000https://ramdi.fr/github-stars/pinchtab-token-efficient-chrome-automation-for-ai-agents-with-go/PinchTab is a Go HTTP server enabling AI agents to control Chrome instances efficiently by extracting structured text, cutting token costs 5-13x compared to screenshots. Local-first, multi-instance, secure.