Repositories
that earned
their place.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

The agent that grows with you

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

The agent engineering platform.

The API to search, scrape, and interact with the web at scale. 🔥

100+ AI agent and RAG applications you can actually run. Curated collection of production-ready AI apps.

An open-source AI agent that brings the power of Gemini directly into your terminal.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

JavaScript API for Chrome and Firefox

A collection of MCP servers.

Official reference implementations of MCP servers for filesystem, GitHub, Brave Search, Puppeteer, and more.

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

🙌 OpenHands: AI-Driven Development

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Meta-prompting system for Claude Code. Spec-driven development framework for structured AI code generation.

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

omo; the best agent harness - previously oh-my-opencode

Universal memory layer for AI agents. Persistent, personalized memory that works across any LLM and framework.

Up-to-date code documentation for LLMs and AI editors. Real-time docs fetched for any library or framework.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Transform any folder of code or documentation into an interactive knowledge graph for AI agents.

Adaptive AI web scraping framework with stealth capabilities. Intelligent extraction for AI agents.

Essential LLM API gateway. Call 100+ LLMs with unified interface, rate limiting, and cost tracking.

Production-grade engineering skills for AI coding agents from Google. Agent capabilities and prompts.

Curated skills, hooks, orchestrators, and tools for the Claude Code ecosystem. Community-driven resource hub.

Interactive knowledge graphs for any codebase. Explore, understand, and navigate complex code visually.

Chrome DevTools for coding agents

Extracted system prompts from Anthropic - Opus 4.7, Opus 4.6, Sonnet 4.6. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google Gemini - 3.5 Flash, 3.1 Pro, 3 Flash, Antigravity. xAI - Grok. Github Copilot. Perplexity, and more. Updated regularly.

Build, run, and manage agent platforms.

Curated configuration files for enhancing the Cursor AI editor. Community-driven rules and setup collection.

Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.

Teams-first multi-agent orchestration system for Claude Code. Run multiple Claude Code agents in parallel.

Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

Event-driven agentic workflow engine. Orchestrate complex multi-step AI agent workflows with durability.

Frontend stack for building AI copilots and agents into any React or Angular app with generative UI.

GitHub's official MCP Server

An AI prompt optimizer for writing better prompts and getting better AI results.

Open-source AI code editor. A Cursor alternative with built-in AI chat, code completion, and agent features.

1000+ toolkits and integrations for building AI agents. Connect agents to any API, tool, or service.

AI knowledge curation system from Stanford. Generates full-length research reports with citations from web sources.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Barebones agents that think in code. HuggingFace's minimalist agent library with Hub integration.

Deep research agent. Web + local sources, detailed reports with citations. The most popular open-source deep research tool.

AI-powered task management system for Cursor, Lovable, and other AI editors. Break down complex tasks.

Lightweight multi-agent framework from OpenAI. Build, sandbox, and orchestrate AI agents with guardrails.

AI-first visual design tool. Edit your React app visually like Cursor for designers. Real-time component editing.

🚀 The fast, Pythonic way to build MCP servers and clients.

Context database for AI agents. File system paradigm for agent memory with self-evolving capabilities.

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

Production principles for LLM-powered software. Best practices for building reliable AI agent applications.

Memory engine and API for AI agents. Fast, scalable memory-as-a-service for persistent agent context.

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

AI-powered browser workflow automation. Combines LLM with computer vision for robust browser automation.

Industry standard for testing prompts, agents, and RAGs. Evaluate LLM outputs across providers and models.

Browser extension for no-code automation. Connect blocks visually to build complex browser workflows.

Durable execution platform for AI agents and workflows. Industry-standard for reliable multi-step orchestration.

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

Debug, evaluate, and monitor LLM applications. Full observability for AI agent traces and performance.

Leading open-source deep research agent from Alibaba. Advanced multi-step research and analysis.

Framework for evaluating LLMs and AI systems with standardized benchmarks and custom test suites.

In-page GUI agent. Control web interfaces with natural language instructions and visual understanding.

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

Agent Operating System in Rust. MCP-native agent runtime with sandboxing and process management.

Dev-first open-source autonomous AI agent framework. Build, manage, and run useful autonomous agents.

Type-safe AI agent framework built on Pydantic. Structured outputs, dependency injection, and OpenTelemetry tracing.

Open-source computer-use agent infrastructure. Sandboxed environments with SDKs for agent deployment.

337 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.

Agent AI observability, monitoring, and evaluation. Trace, debug, and optimize agent performance.

🪄 Create rich visualizations with AI

AI coding agent for large, complex tasks. Plans and executes changes across dozens of files with rollback.

Step-by-step vibe coding course for beginners. Learn to build software using natural language and AI.

Build and deploy managed AI agents and workflows. Durable execution with automatic retries and observability.

MCP server providing Figma layout information to AI agents for design-to-code workflows.

Structured text generation for LLMs. Generate JSON, regex, SQL, and other structured outputs reliably.

Secure sandboxed cloud environments for AI agents. Industry standard for running untrusted agent code.

Zero-effort MCP server from your FastAPI endpoints. Expose any FastAPI route as an MCP tool with auth.

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

AI-powered code review automation. Automatically review PRs, generate descriptions, and suggest changes.

Microsoft's official SDK for building, orchestrating, and deploying AI agents with multi-agent workflows.

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

AI Data Runtime for agents. Multimodal data lake combining vector storage with version control.

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

Build effective agents using Model Context Protocol and simple workflow patterns

The fastest and most accurate file search toolkit for AI agents, Neovim, Rust, C, and NodeJS. Typo-resistant path and content search with frecency ranking.

Specification and documentation for the Model Context Protocol

GitHub Copilot and Codeium extension for Xcode. AI code completion and chat for Apple developers.

Extensible AI workflow development framework from ByteDance. Visual builder for complex AI pipelines.

24/7 AI Workforce platform. Self-improving agents with memory, RAG, and 100+ LLM support.

Deep research on private data. Open-source alternative for secure, private document analysis.

Browser API for AI agents. Batteries-included sandbox with session management and stealth features.

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

MCP server for terminal control, file search, and diff editing. Gives Claude full desktop autonomy.

Open-source LLM observability platform. One-line integration to monitor, evaluate, and debug AI agents.

Annotate and review AI coding agent plans and code diffs. Visual diff review for agent-generated changes.

Evaluation and testing framework for LLM agents. Red-teaming, vulnerability scanning, and quality assurance.

Open-source AgentOS continuation of AutoGen. Multi-agent conversations with A2A and MCP support.

A tremendous feat of documentation, this guide covers Claude Code from beginner to power user, with production-ready templates for Claude Code features, guides on agentic workflows, and a lot of great learning materials, including quizzes and a handy "cheatsheet". Whether it's the "ultimate" guide to Claude Code will be up to the reader :)

Memory library for building stateful AI agents. Continual learning and persistent memory management.

Review-first terminal diff viewer for AI-assisted coding. Focus on meaningful changes in agent-generated code.

Open-source agent engineering platform. Build, evaluate, and improve AI agents collaboratively.

Full-stack AI Red Teaming toolkit. Agent scanning, MCP scanning, jailbreak evaluation, and prompt injection testing.

Policy enforcement, zero-trust, and sandboxing for AI agents. Covers OWASP Agentic Top 10 vulnerabilities.

Multi-vector search engine with semantic code search for terminals and coding agents. Combines regex filtering with semantic ranking, fully local.

Catches bad React code generated by AI agents. Automated quality checks for AI-generated React components.

A curated collection of resources spanning AI-powered coding agents, development environments, and productivity tools for the modern AI-assisted developer workflow.