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
agency-agents: Install Role-Specific AI Agent Instructions
A large collection of specialized AI agent instruction files, organized by professional role and supported by scripts for installing them into compatible coding tools. Useful when you want reusable role-specific workflows rather than a single general-purpose prompt.
MiroFish: Simulate Agent Societies to Explore Possible Futures
MiroFish uses LLM-powered agents and a knowledge graph to simulate social scenarios from source material. It is aimed at teams and individuals exploring public opinion, policy, financial signals, or creative what-if scenarios before making decisions.
clawflows: Manage Reusable OpenClaw Agent Workflows
ClawFlows installs and manages reusable workflows for OpenClaw agents, including scheduled routines and on-demand tasks. It suits OpenClaw users who want to extend agent behavior with editable workflows instead of maintaining scattered instructions.
get-shit-done: Structure Claude Code Work with Prompts and Specs
get-shit-done was a lightweight system for meta-prompting, context engineering, and spec-driven development with Claude Code. This repository is archived; development has moved to GSD Core in the Open GSD repository.
skills: Apply Engineering Workflows to Coding Agents
A collection of composable agent skills that brings engineering practices such as requirements clarification, TDD, debugging, and code design into coding-agent workflows. It suits developers who want to guide agents without adopting an end-to-end process framework.
OpenHuman: Run a Modular AI Agent Harness
OpenHuman is a Rust-based agent harness available as a desktop app, browser UI, terminal client, and embeddable library. It connects configurable language models, memory, search, tools, and workflows for people building or using persistent AI agents.
agentmemory: Persistent Memory for AI Coding Agents
agentmemory gives coding agents persistent, searchable memory across sessions and tools. It captures work through agent integrations and exposes shared memory through MCP and REST, with a local-first runtime built on iii-engine.
CloakBrowser: Automate Chromium with Modified Fingerprints
CloakBrowser wraps a custom Chromium build with source-level fingerprint changes and Playwright- and Puppeteer-compatible APIs. It is aimed at browser automation and web scraping where standard browser automation is frequently flagged by bot detection.
ai-website-cloner-template: Recreate Websites as Next.js Apps
A template that equips AI coding agents to inspect a website and recreate it as a Next.js application. It suits developers rebuilding sites they own, recovering lost source code, or studying real-world interface implementations.
claude-code-best-practice: Learn Claude Code Workflows and Practices
A community-maintained guide to Claude Code practices, configuration, agents, skills, and development workflows. It helps developers move from ad hoc prompting toward repeatable, agentic engineering, with examples and links to further resources.
claude-plugins-official: Discover Plugins for Claude Code
An Anthropic-managed directory of internal and community plugins for Claude Code. Browse and install plugins through the built-in plugin system, or use the directory as a reference when evaluating plugin structure and marketplace submissions.
codegraph: Give Coding Agents a Local Code Knowledge Graph
CodeGraph builds and maintains a local graph of code structure so AI coding agents can retrieve relevant source, call paths, and change impact without exploring files one by one. It connects to multiple agents through MCP and supports many languages.