Open Source AI Agents
Discover 406 open source AI Agents repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI Agents projects here are most often combined with Python, Developer Tools and MCP. Last updated October 4, 2026.
406 repositories · updated October 4, 2026
codex-plugin-cc: Use Codex from Claude Code
A Claude Code plugin that connects your existing local Codex CLI for code reviews and delegated tasks. It suits developers who want Codex in their current workflow, with background job controls and session handoff.
ai-engineering-from-scratch: Learn AI by Building It
A free, MIT-licensed curriculum that teaches AI engineering through runnable lessons and hands-on artifacts. It covers foundations through LLMs, agents, protocols, and production, with paths for beginners and experienced developers.
FinceptTerminal: Research Markets with a Desktop Finance Terminal
FinceptTerminal is a native desktop application for financial research, combining market data, analytics, AI agents, and paper trading. It suits individual researchers and developers who can bring their own data and model credentials and accept the AGPL-3.0 license.
andrej-karpathy-skills: Guide Claude Code Toward Safer Changes
A compact set of coding guidelines for Claude Code, based on Andrej Karpathy’s observations about common LLM coding mistakes. It encourages clarification, simpler implementations, focused edits, and verifiable goals.
skills: Add .NET Skills to AI Coding Agents
A curated collection of portable skills and host-specific agents for .NET and C# coding agents. It helps agents handle development, testing, upgrades, diagnostics, and other specialized .NET tasks.
chrome-devtools-mcp: Give Coding Agents Chrome DevTools Access
Chrome DevTools MCP lets coding agents control and inspect a live Chrome browser through MCP or a CLI. Use it for browser automation, debugging, and performance analysis when your workflow needs access to real browser behavior.
Anthropic-Cybersecurity-Skills: Give AI Agents Security Playbooks
A library of structured cybersecurity workflows for AI agents, covering 34 security domains and mapped to six industry frameworks. Use it to provide compatible agents with practical guidance for authorized security work.
multica: Coordinate AI Coding Agents and Human Teams
Multica is a self-hostable workspace for assigning issues to AI coding agents and collaborating with them through review. It connects existing agent CLIs to team workflows, with runs and decisions linked to each issue.
opencode: Work with an Open Source AI Coding Agent
OpenCode is an open source AI coding agent for developers who want AI assistance in their coding workflow. It offers build and read-only plan agents, a terminal UI, and desktop apps in beta.
agentic-ai-prompt-research: Study Coding Assistant Prompt Design
An independent research project reconstructing prompt patterns and coordination mechanisms used by agentic coding assistants. It is intended for AI builders, prompt engineers, and security researchers, not as a verbatim copy of any proprietary system.
apm: Manage Dependencies for AI Agent Setups
APM manages AI-agent instructions, skills, prompts, plugins, and MCP servers through a project manifest and lockfile. It helps teams reproduce agent configurations across supported coding clients and apply installation security and policy controls.
flyai-skill: Search Travel and Booking Options with AI Agents
FlyAI connects Claude Code, OpenClaw, and compatible agents to Fliggy travel search through a command-line tool. Use it to find flights, hotels, trains, attractions, and other travel services and receive structured results with booking links.