Find the public repos shaping how AI agents work.

Role-based CEO, design, engineering, release, docs, and QA workflows for agentic coding.

Production engineering skills for AI coding agents from Addy Osmani.

Marketing skills for Claude Code and AI agents across CRO, copywriting, SEO, analytics, and growth engineering.

A curated list of Claude Code skills, hooks, slash commands, orchestrators, apps, and plugins.

A collection of DESIGN.md files that teach coding agents how popular design systems behave.

A collection of Cursor rule files that shape AI editor behavior across frameworks and workflows.

Guides, papers, lessons, notebooks, and resources for prompt engineering, context engineering, RAG, and agents.

A large open-source prompt collection formerly known as Awesome ChatGPT Prompts.

A curated directory of MCP servers that add tools and data sources to AI agents.

GitHub MCP server for giving agents structured access to GitHub workflows.

Open-source coding agent CLI for terminal-based software work.

Public Claude Code repo and docs for studying agentic coding workflows.

Terminal-first AI coding agent with provider flexibility and project workflows.

AI pair programming in the terminal with Git-aware code edits.

Open-source autopilot for VS Code and JetBrains with local and hosted models.

Framework for building conversational, tool-using, and multi-agent applications.

Framework for orchestrating role-based autonomous AI agents.

Framework for building applications with LLMs, tools, retrieval, and agents.

Graph-based framework for controllable, stateful agent workflows.

Data framework for connecting private documents and tools to LLM applications.

Open-source platform for building agentic workflows, RAG apps, and model operations.

Drag-and-drop builder for LLM flows, tools, retrieval, and agent chains.

Workflow automation platform that can connect agent steps to business systems.

Visual framework for building and testing agent and RAG workflows.

Memory layer for AI agents that need persistent user and task context.

Long-term memory service for assistants with user, session, and facts context.

Framework for stateful agents with memory, tools, and long-running behavior.

MCP server that gives compatible agents semantic memory capabilities.

Self-hosted AI interface with document workflows, tools, and local model support.

Desktop and server workspace for private documents, agents, and retrieval.

Reference implementation for private document ingestion and question answering.

RAG engine focused on document understanding, parsing, and knowledge workflows.

Open-source tracing, prompt management, and evaluation for LLM applications.

Open-source observability and eval tooling for LLM, RAG, and agent systems.

CLI and framework for testing prompts, models, and agent behaviors.

Evaluation framework for testing LLM outputs, RAG quality, and agent behavior.

MCP server that gives agents structured browser automation through Playwright.

Toolkit for connecting AI agents to browser actions and web tasks.

AI browser automation for repetitive web workflows and form-heavy tasks.

Turn GitHub repositories into digestible text context for LLMs and agents.

Pack repository contents into agent-friendly files for analysis and coding tasks.

Coding agent toolkit that uses language-server based semantic code understanding.

Benchmarks and reports useful for comparing coding agent model performance.

Curated resources for generative AI tools, agents, courses, and references.

Hands-on examples for RAG, agents, LLM apps, and production AI engineering.