anthropics/claude-cookbooks offers Jupyter Notebook recipes demonstrating practical Claude API usage, including sub-agent orchestration, multimodal vision, and RAG patterns.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
A curated list catalogs 80+ AI coding agent orchestration tools, revealing a fragmented ecosystem around git worktree isolation, parallel execution, and multi-agent coordination.
A curated directory cataloging over 200 production-ready open-source AI projects across the machine learning stack, from training frameworks to self-hosted UIs.
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.
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.
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.
