Open-source AI agents

AetherLabsAI

RSIAgent

★ 607

A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory.

InternScience

Agents-A1

★ 607

Scaling the Horizon, Not the Parameters

jaylfc

taOS

★ 607

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

maze-agent

Maze

★ 607

A distributed framework for LLM agents

neo4j-labs

agent-memory

★ 607

A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j.

Enderfga

claw-orchestrator

★ 606

Run Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-agent councils, an OpenAI-compatible endpoint, an MCP server, and an ACP agent any editor can drive.

johnlindquist

mdflow

★ 606

Multi-backend CLI for executable markdown prompts. Run .md files against Claude, Codex, Gemini, or Copilot.

Siddhant-Goswami

100x-LLM

★ 606

Code snippets and examples from the 100x Applied AI cohort lectures.

craigsc

cmux

★ 605

cmux: tmux for Claude Code

julianoczkowski

designer-skills

★ 605

A collection of agent skills for designers who prototype and build with AI coding tools. These skills encode design process so AI follows a structured path instead of producing random output.

SJTUjinmao

ArkEval

★ 605

ArkEval: Benchmarking and Evaluating Automated Code Repair for ArkTS

ahmadawais

ramadan-cli

★ 604

CLI to check Sehar and Iftar times in Ramadan anywhere in the world.

awslabs

fullstack-solution-template-for-agentcore

★ 604

Flexible Fullstack solution template for production-ready deployments of any use case on Amazon Bedrock AgentCore.

joreilly

FantasyPremierLeague

★ 604

Fantasy Premier League Kotlin/Compose Multiplatform sample

OpenMinis

iCTRL

★ 604

An AI-friendly iOS/iPadOS automation testing tool built on XCUITest, but more than a testing tool: agents like Codex, Claude Code, Hermes, OpenClaw and Minis can operate your iPhone or iPad wirelessly through an encrypted JSON-RPC 2.0 API (tap, type, read the screen, launch apps, and more).

SalesforceAIResearch

MCP-Universe

★ 604

MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.

sharpdeveye

maestro

★ 604

Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6 more.

twisted

treq

★ 604

Python requests like API built on top of Twisted's HTTP client.

ww-w-ai

bkit-claude-code

★ 604

bkit Vibecoding Kit - PDCA methodology + Claude Code mastery for AI-native development

24kchengYe

MemoMind

★ 603

Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.

aldefy

compose-skill

★ 603

Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf, and more.

fendouai

CodexSaver

★ 603

Make Codex cheaper without making it dumber with DeepSeek.

modiqo

waggle

★ 603

Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.

qybaihe

mu

★ 603

mu (μ): a coding agent that thinks before it acts. A small, fast judge makes the routine calls, the big model does the work. Built on pi and AionUi.