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
SPONSIO - AI AGENT SECURITY
Sponsio offers deterministic security solutions for probabilistic AI agents, minimizing risks of unpredictable behavior.
★ 472 · PythonHCLI WEBSITES READY FOR AI
Hycli turns website tasks into verified CLI and MCP actions, providing a local dashboard and support for 20 languages. Written in Rust, it focuses on local automation of
★ 471 · RustTHREAT MODELING FOR AI AGENTS
grim-prompter points Claude Code, Codex, or any agent at your repo and delivers an evidence-traced threat model. Covers 36 architectures and 29 methods (LINDDUN, STRIDE).
★ 469DSH‑IOS: iOS Simulator In Chat
The DeepSeek Harness plugin for iOS lets you launch the simulator and a real device directly in the chat, controlling UI via accessibility, OCR, and a string list.
★ 467 · TypeScriptRYUGI: ARTIFACTS FOR AI AGENTS
Ryugi provides artifacts for coding agents: mockup artboards, design docs, whiteboards, HTML benches, and verify reports. Comments on artifacts are sent back to the agent
★ 467 · JavaScriptAVIBE - Your Local AI Agent
Avibe is a local OS for AI agents that lets you run Claude Code, Codex, and OpenCode directly in your browser or any chat app.
★ 466 · PythonAGENT-STYLE: 21 RULES
agent-style provides 21 style rules for AI agent code and text. Connect it to Claude, Codex, Copilot, Cursor, or Aider — and the output becomes professional.
★ 465 · PythonHIROUTE — SMART AI MODEL ROUTER
Local router routes routine tasks to cheap models, complex ones to powerful. Reduces Codex and Claude Code subscription costs while preserving quality. Written in Rust.
★ 465 · RustAGENTHOUND AGENT HUNT
Offensive security framework for AI agent infrastructure: reconnaissance, credential looting, model exfiltration, poisoning, and attack‑path analysis.
★ 464 · GoPARALLEL AUDITOR OF SMART CONTRACTS
Bountyforge — a set of skills for Claude Code, launching parallel agents for auditing smart contracts (EVM, Move, Solana, TRON), web and API security. It prepares reports
★ 464 · PythonAGENTGG: AI-POWERED SAST SCANNER
Open-source agentic SAST engine behind hundreds of published zero‑days. Over 100 AI agents analyze any repository or PR diff, supporting the use of your own model.
★ 464 · TypeScriptMUXIN UNIFIED CONTROL FOR AGENTS
Muxin unifies all your computers (Mac, Linux, Windows) into a single app. You can manage AI‑agent sessions, desktops, files, logs and GitHub repositories via an MCP serve
★ 464 · RustSwarmVault: Local Wiki for LLM
Open tool for building knowledge graphs, RAG database, and agent memory. An Obsidian alternative for personal knowledge management and AI second brain.
★ 463 · TypeScriptAGENTS: AI Agent for Data
Agents — a toolkit for creating AI agents that automate data engineering. It supports ETL pipelines, LLM, and workflow management.
★ 463 · PythonCLOUD SKILL FOR PRODUCT VIDEO
Claude Code‑skill creates Dribbble‑level product launch videos from code: infinite shape, springs, cursor‑driver, beat‑synced SFX and 60 fps with motion blur. Works with
★ 463 · JavaScriptMIRA OSS: AI IN A BOX
Modular OS with self-configuring tools and self-learning memory. Run and chat via cURL requests.
★ 461 · PythonALWAYS-ACCOMPANY - AI PARTNER FOR CODE
The always-accompany project creates an AI agent with shared memory and context for chat, code, and collaboration — like in science fiction.
★ 460 · JavaScriptLAUNCH AI AGENTS IN OBSIDIAN
The plugin lets you run Claude Code, Codex and other CLI agents directly inside Obsidian notes. You get an interactive terminal with AI support without leaving your works
★ 459 · JavaScriptEVOLVING AGENT FOR TEAMS
The director agent studies the team's work via CLAUDE.md and linked memory statements, forms a plan and delegates tasks to Claude Code or local models. Lessons are stored
★ 458 · TypeScriptWMUX - tmux alternative for AI
Windows alternative to tmux for Claude Code, Codex, and Gemini CLI with MCP browser automation support. No WSL.
★ 455 · TypeScriptAEON — UNSUPERVISED AUTONOMOUS AGENT
Autonomous agent framework. Set up once — forget forever, no approval loops or constant supervision.
★ 453 · TypeScriptOKF SKILLS FOR CLAUDE CODE
A toolkit for creating, validating, and visualizing Open Knowledge Format packages in Claude Code.
★ 452 · PythonHYPHA Agent Framework
TypeScript framework for production‑grade LLM agents. Enables rapid creation and management of agents via a flexible harness architecture.
★ 452 · TypeScriptHEYM: AI Automation Server
Self-hosted platform for AI workflows with a visual canvas, agents, RAG, HITL, MCP, and observability in a single runtime.
★ 451 · PythonNIGHTSHIFT: AUTONOMOUS CODING SHIFTS
Nightshift runs long autonomous sessions for Cursor, Codex, and Claude Code. Persists state, recovers from crashes, and gives a clean report: done, in progress, parked, o
★ 451 · ShellAI AGENTS ON AZURE AND GPU
Repository with code, benchmarks, and guides for AI agents and Deep Learning. Deployment on Microsoft Foundry and Azure, fine-tuning, inference optimization, and GPU test
★ 451 · Jupyter NotebookASQAV-SDK - TRUST FOR AI AGENTS
Python/TypeScript SDK for signed action receipts of AI agents, policy control, and auditing. Works with LangChain, CrewAI, and MCP.
★ 449 · PythonSMITHERS - KEEP CODE UNDER CONTROL
Smithers ensures reliable execution of agent code: it survives failures, waits for human confirmation, and rolls back errors. It supports Claude Code, Codex, Gemini, and
★ 449 · JavaScriptACCESSIBILITY AGENTS FOR CODE
A set of eleven agents checking code for WCAG 2.2 AA compliance so that AI tools generate accessible code.
★ 448 · JavaScriptN8N-CLAW: AUTONOMOUS AI AGENT
An autonomous AI agent on n8n with adaptive RAG memory, skills via MCP, and proactive task management.
★ 447 · ShellPASS APP STORE REVIEW
Project collects 117 App Store and Google Play rejection patterns with fixes. Checks Privacy Manifest, Data Safety, and 95 legal deadlines (EU AI Act, DSA, COPPA). Includ
★ 447 · ShellSANDBOXED.SH - SAFE ENVIRONMENT FOR AI
Isolated sandboxes, a skills library, encrypted secrets, and OKX security checks for autonomous on-chain AI agents.
★ 446 · RustRUNPROMPT: LLM PROMPTS FROM TERMINAL
Run LLM prompts directly from the command line. Simple, fast and convenient.
★ 446 · PythonHERMES-WEB-SEARCH-PLUS AI Agent
Hermes Web Search Plus equips the AI agent with real web sources, eliminating hallucinations. It supports multi‑provider search and a local key‑free DonSeTch mode.
★ 444 · PythonOPENABCODE — SMART AGENT FOR CODE
OpenABCode is a TypeScript agent that intelligently routes code tasks to the most suitable LLM models.
★ 444 · TypeScriptPLATFORM FOR AI AGENTS
The open CAIPE platform helps create, deploy, and manage AI agents and their workflows on TypeScript.
★ 444 · TypeScriptMETIS: BOOSTING AI/LLM CODING EFFICIENCY
Metis is a TypeScript agent that boosts AI/LLM coding performance by 50%. It has already garnered 297 stars on GitHub and offers ready‑to‑use skills for automating testin
★ 443 · TypeScriptULTRACONTEXT FOR AI AGENTS
Ultracontext — open source context infrastructure for AI agents. Automatically captures and shares agent context everywhere.
★ 442 · JavaScriptSELF-HOSTED JIRA ALTERNATIVE
Self-hosted open-source work management platform and Jira alternative (AGPL v3). Written in Go, runs in Docker. 412 stars on GitHub.
★ 442 · GoPORTABLE MEMORY FOR AGENTS
Portable semantic memory for AI agents: core, TS‑SDK, framework adapters, MCP server, CLI, and plugins.
★ 440 · TypeScriptMARM-MEMORY: LOCAL AI MEMORY
Memory layer for Claude Code and Cursor: combines session history, code indexes, and concept graphs in SQLite, providing cloud‑free context.
★ 438 · PythonAgent Environment Framework
Framework for building realistic reinforcement learning environments with collaboration tools for researchers and engineers.
★ 438 · PythonAI AGENT COORDINATION PROTOCOL
foremerge — open coordination protocol for coding agents over Git. Catches intent conflicts before code conflicts appear. Written in Rust, works via CLI and MCP.
★ 437 · RustFILE-BACKED HARNESS FOR AI AGENTS
repo-harness is a file-backed harness for reliable Claude Code and Codex sessions. Saves context to files, restores state after crashes, and manages agentic-workflows via
★ 436 · TypeScriptXiryn Personal AI Agent
Open‑source personal agent that runs isolated Linux desktops in Docker, supports any LLM with your keys, and offers an encrypted vault controllable via Telegram.
★ 435 · TypeScriptEDGECHAINS: GENAI IN JAVASCRIPT
Full‑stack library for working with AI. Prompts and chains are managed declaratively via jsonnet, not hidden in classes.
★ 434 · JavaScriptDEVELOPER DOCUMENTATION
AnythingLLM — AI platform for working with documents, YouTube, and hosting resources. Boost your ideas!
★ 433 · MDXPRYSAI PLAYBOOK: COMPLETE LLM GUIDE
LLM playbook on practice: 8 locales, unified core, Codex track and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, Grok.
★ 433 · PythonCLI Agent Orchestration
Audit-grade orchestration of multi-agent CLI tools with HMAC logs, agent signatures, and artifact lineage — compliance-ready.
★ 432 · PythonPLUGIN LIST FOR DEEPSEEK HARNESS
A curated list of plugins, skills, MCP servers, patch/profile layers for DeepSeek Harness. Includes visualization tools,PPT generation,coding,agents, and auto‑research lo
★ 432 · TypeScriptMCP AUTOMATION FOR WINDOWS SANDBOX
sandbox-mcp — MCP server and CLI for automating Windows Sandbox. Creates fresh throwaway machines for app testing in seconds. Ideal for UI automation and isolated checks.
★ 432 · JavaScriptMCPTOON: SAVES 99% OF MCP TOKENS
Standard MCP discovery burns 71,929 tokens. mcptoon drops it to 581 — 99.2% savings. Zero dependencies.
★ 431 · HTMLDOTFILES: PERFECT MACOS SETUP
My configs for macOS: Neovim, Zsh, Ghostty, and Tmux — all in one repo for a quick work‑environment setup.
★ 430 · ShellCLAUDE SKILLS: 172 MODULES
172 ready-to-use Claude skills for sales, marketing, design, engineering, and AI agents. Developed and maintained by OneWave AI.
★ 430AI AGENTS IN SAFE
SAW — AI-agent framework on SAFe for multi-agent processes in any domain.
★ 430 · ShellAI AGENTS PARALLEL CODE
Workspace for AI agents. Specialists plan tasks, and Claude Code, Codex and Cursor work in parallel — locally or in the cloud.
★ 430 · JavaScriptSTIRRUP: Lightweight Framework for Agents
A minimalist Python framework for building AI agents. 428 stars on GitHub — community‑validated.
★ 428 · PythonContext Layer for AI Agents
Ktx is an executable context layer that lets Claude Code, Codex, and any AI agent precisely query data via MCP using the agent's skills and memory.
★ 427 · TypeScriptIDE FILE TREE FOR CLAUDE CODE
A pane in terminal and Claude Desktop shows files the agent reads and edits. Includes git status, diffs, content search, previews, and guarded paths.
★ 427 · TypeScriptCRAFTBOT - ALL-IN-ONE AGENT
CraftBot — a universal AI agent on Python, capable of performing any tasks: from code to documentation.
★ 426 · PythonNew projects on this topic in Telegram
Telegram →