AI Agents: open-source projects on GitHub
1319 repositories on AI Agents, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
PgGraph — Graph DB for Postgres
An open graph database on top of your existing Postgres. Written in Rust.
★ 243 · RustAI AGENTS IN KUBERNETES
Agyn — an open-source runtime that moves AI agents into company infrastructure with corporate controls.
★ 243 · TypeScriptcodex-bridge - Generate Images and Agents
Generate images via GPT‑Image‑2 and launch GPT‑5 sub‑agents in Claude Code, using only the Codex CLI login — no OpenAI key needed.
★ 243 · ShellTS-BENCH: AI AGENTS BENCHMARK
CLI tool for comparing the performance of AI agents in TypeScript tasks.
★ 243 · TypeScriptDOBERMAN-CORE — PROTECTION FOR AI AGENTS
Doberman-Core intercepts every input, output, and tool call during AI-agent operation, blocking unsafe actions. It works as middleware, checking authorization and applyin
★ 243 · PythonMANAGE AI AGENTS IN TMUX
ccmux lets you run all your AI‑coding agents inside tmux, quickly switch to the one that needs you and move work between them. Create separate worktree sessions for each
★ 243 · TypeScriptJAT: FIRST AGENT IDE
The first agent IDE with a visual panel: live sessions, tasks, code editor, and terminal. Parallel workflows and auto-rules.
★ 242 · SvelteONE API FOR 100+ MODELS
Linten is an open-source AI gateway with a single OpenAI-compatible API for 100+ models. Supports virtual keys, spend tracking, routing, and guardrails. Self-hosted deplo
★ 242 · PythonENVOY: Joint Data Storage
A distributed state store for AI agents, sessions, machines, and organizations in a single location.
★ 241 · ShellLPM - Quick Start AI Workspaces
Start, stop, and duplicate dev projects with one click. Perfect for Claude Code, Codex, and other AI agents. ⭐ 241
★ 241 · TypeScriptLUCARNA MANAGE CODE ANYWHERE
Receive notifications, approve changes, and keep working with Codex, Pi, or Claude anywhere — via Telegram, WeChat, or 飞书, without a single hook.
★ 241 · RustPRECISE GATEWAY FOR AI TOOLS
Local MCP gateway provides a single port for all tools and AI clients. It enables lazy discovery with ~90% token savings, verifies tool integrity and quarantines suspicio
★ 241 · RustYourMemory - AI Memory with Forgetting
Agentic AI memory accounting for Ebbinghaus forgetting curve. On LoCoMo it gives +16pp better recall than Mem0.
★ 240 · PythonAGENT-PULSE AI TRENDS REAL TIME
Agent‑Pulse gathers evidence‑based data on the AI industry: daily trend updates, source updates, and weekly briefs for decisions.
★ 240 · TypeScriptMINIMAL BOX FOR AGENTS
Run the AI agent in an isolated Minimal box on your PC. Build and execute code without risk to the system.
★ 240 · RustAI AGENT CODE TEMPLATE
TypeScript template for Claude Code with sub-agent workflow and automatic quality checks.
★ 239 · JavaScriptGO AI SDK: UNIFIED API
Go AI SDK provides a unified interface for over 21 LLM providers, including OpenAI, Anthropic, and Azure. It supports streaming generation, structured JSON output, and Mo
★ 239 · GoZOTSEEK AI SEARCH IN ZOTERO
ZotSeek adds semantic search to your Zotero library using vector embeddings. The built-in MCP server lets you connect Claude Code and Codex as AI agents for meaning‑based
★ 239 · TypeScriptLLM Bug-Sweeping Benchmark
A Python benchmark that measures how many bugs LLMs can detect and fix across large codebases.
★ 239 · PythonRED-TEAMING AI AGENTS IN PYTHON
Humanbound — adversarial testing engine, SDK, and CLI for AI agents. Runs locally or via Humanbound Platform. 218 stars on GitHub.
★ 239 · PythonADHD — Skill for Coding Agents
Tree of thoughts with dead‑end branch pruning. Parallel reasoning in multiple cognitive frameworks built on Claude Agent SDK.
★ 238 · TypeScriptBEACON-SKILL: AGENT PINGS
Library for exchanging messages between AI agents with support for RTC values and UDP bus. Easy integration into multi-agent systems.
★ 238 · PythonMAESTRO: Agent Audit for Code
Unified task system and decision log for Claude Code, Codex, and CI. Full traceability of agent work.
★ 237 · RustHOMELAB MONITOR DASHBOARD
Plug‑and‑play dashboard for homelab in a single container: monitoring GPU, local‑AI VRAM, Docker, systemd and host health. Built‑in read‑only MCP server gives AI agents a
★ 236 · PythonANIMAWORKS: AGENT CODE
Autonomous AI agents with brain-like memory: they grow, consolidate, and forget. Supports Claude, Codex, Gemini, Cursor, and Ollama.
★ 235 · PythonSecurity for AI Agents
Open solution for controlling AI agents: rules, credentials, and action audit.
★ 235 · GoKSoR SDK for Knowledge
KSoR is an open TypeScript SDK for building governed and authoritative knowledge systems that work with humans and AI agents. It forms the foundation for an AI-native kno
★ 235 · TypeScriptRAILTRACKS FRAMEWORK FOR AI AGENTS
Railtracks is a Python framework for building resilient agentic systems. It simplifies orchestration of AI agents, provides fault tolerance and observability tools. It su
★ 235 · PythonEVALUATE AGENTS WITH CALIPER
Caliper runs your real agent with skills, MCPs, and rules and without them, showing what actually helps and how many tokens it costs. Supports Claude Code, Codex, Pi, and
★ 235 · PythonAGENT SKILLS: AI PROJECT
A set of ready-made skills for AI agents: Clawdbot, Claude Code, and Codex. Speeds up development and expands automation capabilities.
★ 234 · PythonLOBU AGENT PLATFORM
Open-source platform for managing corporate agents: shared company context, isolated execution, and approval system.
★ 234 · TypeScriptLong-Term Memory for AI
Open-source vector-free long-term memory engine for AI agents, delivering SOTA results on LoCoMo and LongMemEval with substantial context reduction.
★ 234 · PythonSUPERPOWERS CLAUDE CODE FOR SYMFONY
Claude Code plugin for Symfony 7.4 LTS and 8.x adds 44 skills, 7 AI subagents and 13 commands for working with API Platform, Doctrine ORM, testing Pest/PHPUnit, Messenger
★ 234 · TypeScriptDeepSeek Harness Roleplay Plugin
A SillyTavern plugin adding long-term memory, branching dialogues, and hybrid retrieval for immersive roleplay.
★ 234 · JavaScriptAMUX: Multiplexer for AI Code
amux launches dozens of parallel Claude Code agents in tmux without supervision. Set it up once and enjoy autonomous AI coding.
★ 233 · HTMLAGENT CORTEX: AI MAP
Curated map of frameworks, protocols, and tools for creating AI agents.
★ 233 · JavaScriptSUPERMOD: NEW SKILLS
Open agents and tool schemas for Superior Trade – create, test, and deploy strategies on Hyperliquid.
★ 232 · JavaScriptALL PROMPTS CLAUDE IN ONE
All official Claude prompts in one repository: verbatim, dated and source-linked, from Claude Fable 5.2 to Haiku 3. 23 models from Anthropic's release notes, plus analysi
★ 232 · PythonSIMPLERLLM: Easy LLM Use
The library simplifies calling LLM via a unified Python interface, supporting popular providers and quick AI integration into projects.
★ 231 · PythonAUTORESUME AI SESSIONS
unsnooze automatically resumes Claude Code, Codex, Grok, Qwen, Kimi, OpenCode, and Antigravity sessions after 5-hour and weekly limits reset. Works in tmux, Zellij, VS Co
★ 231 · JavaScriptMETA-LLM-CHARTER - AI Engineer Rules
Eleven rules and one meta‑rule that turn LLM agents into disciplined lead engineers.
★ 230 · TypeScriptFORGE: Agent Runtime
Forge is an open runtime for Anthropic agent skills. Write a SKILL.md, compile to a portable agent, and run anywhere.
★ 230 · GoVIBE — BOILERPLATE FOR AI APPS
Toolkit for building AI apps on the ibl.ai platform. The iblai-app-cli CLI and @iblai/iblai-js SDK spin up a Next.js project with SSO, chat, profiles, notifications, and
★ 230 · TypeScriptUniversal SDK for AI Agents
Composio is an SDK for connecting AI agents to numerous platforms and automation tools.
★ 228 · TypeScriptMantisHack Simple Scanner
MantisHack is a Python script for finding and exploiting vulnerabilities in MantisBT. It automates testing and generates security reports.
★ 228 · PythonGEM-TEAM: AI CODING
The gem-team project turns AI code generation into a transparent engineering process with versioning, tests, and review.
★ 228IRIS-AI: REAL ASSISTANT
IRIS-AI is a TypeScript‑based desktop assistant that combines voice control, task automation, memory, computer vision, web search, and workflow tools in a single interfac
★ 228 · TypeScriptOPEN GAME WIKI TEMPLATE ON ASTRO
AnvilWiki — free game wiki template on Astro and Cloudflare Pages. Static, zero-JS, with AI-native content workflow. Unlimited bandwidth and 201 stars on GitHub.
★ 228 · TypeScriptCOMMON SKILLS FOR AI AGENTS
Project agents provides shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents. It simplifies creating custom skills and ensures comp
★ 227 · PythonBACKTOTAL LOCAL API EMULATOR
Backlot emulates Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3 and other services with real responses, pagination, auth and ACL on your data. Run locally in minute
★ 227 · PythonRECONSTRUCT LIGHT PORTRAIT
A portrait editing skill: restores key light, fill, shadows and background atmosphere using a director‑led lighting workflow. Simultaneously returns clean, healthy skin w
★ 227 · PythonAGENTCREW: MULTI-AGENT CHAT
Python chat application with multi-agent system, multiple models, and MCP support. 204 stars on GitHub.
★ 226 · PythonCOLLECTIVE INTELLIGENCE AI
A collective intelligence engine where tens of thousands of AI models collaborate through diverse coordination strategies.
★ 226 · TypeScriptClaude Skills for Websites
Universal Claude skills for the full website creation cycle: branding, design, content, SEO, development, operation, growth, and research.
★ 225 · PythonLazy AI Agent
The ponytail project makes your AI agent as lazy as possible: it writes only the code that is indispensable, following the principle of a lazy senior developer. This appr
★ 225 · JavaScriptELVES: AUTONOMOUS DEVELOPMENT
Elves is an autonomous multi-batch development skill for Claude Code and Codex that writes and tests code while you sleep.
★ 225 · PythonGAIA-UI AI Agent Components
A set of beautifully styled TypeScript components for quickly creating AI agents. Ideal for developers who value design.
★ 225 · TypeScriptGUARDANA AI MODEL PROTECTION
Guardana scans model artifacts, live endpoints, MCP servers, and agent traces for security threats. It generates reproducible evidence for release decisions.
★ 225 · PythonWEAM: AI Agent for Teams
A web app for teams of 20+ people with built‑in LLM connections, shared access to chats and agents. Fully responsive Next.js + Node.js stack.
★ 224 · TypeScriptOPEN GENI: SELF-HOSTABLE AGENT SERVICE
Opengeni — an open self‑hostable agent service for organizations, providing durable and replayable agent sessions, human approvals, and governed credentials. It runs in i
★ 224 · TypeScriptNew projects on this topic in Telegram
Telegram →