Autonomous AI agents that perform tasks independently
Multi-agent AI framework with A2A protocol support, group chat, persistent memory, and extensible tool system
Build LLM-powered systems as typed, testable Python software — not prompt strings
Offline Expert Agent — local RAG, agent mode, plugins, privacy-first
Raeli Savitt
SWARM: System-Wide Assessment of Risk in Multi-agent systems - A Distributional AGI Safety framework
KotobaCore Project
Japanese semantic understanding engine for LLM, RAG, SNS analysis, and AI agents
llm-wiki contributors
Installer for LLM-native Obsidian Markdown knowledge vaults.
Self-correcting voice agent supervisor — three-tier Mirror Judge (deterministic + classifier + LLM) catches mistakes mid-call and ships PRs to fix them.
...morethClaws
Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
...moreSonicBotMan
Complete ETCLOVG framework for AI Agent workflows - DAG+FSM orchestration, Ebbinghaus memory, discipline routing, skill evolution, trace system, governance. 80+ tests, zero deps, 7/7 layers.
...morewasintoh
Talk to your LINE Official Account through AI. 27 tools for broadcasts, audiences, rich menus, Flex messages, coupons & insights — works with Claude Cowork, Claude Code, Cursor, and any MCP-compatible host. Zero infrastructure, free-tier ready.
...morelebek
Mod your favourite games without writing code. Modmixer is a desktop app that decompiles/indexes your game and provides your AI coding LLM (Claude, Codex, Kimi, Deepseek etc) with tools to efficiently build and test mods.
...moreEA-Studio-SHARK
claude-code llm anthropic developer-tools chinese model-context-protocol cursor windsurf🔥 China Real-time Trending MCP Server | 中国实时热搜聚合 — 微博/知乎/B站/百度/抖音/IT之家 | 让 Claude/Cursor 实时获取中文热点
...moremohamedatr1
Multi‑tool AI agent with 18 tools, 3 LLM providers, multilingual OCR, translation, transcription, and file I/O. Runs offline or in the cloud.
...morecavinwong
🦞 The application development framework for OpenClaw — build, test, and deploy AI agent apps
kkkayye
Independent Socartes project with multi-agent orchestration, RAG, MCP tool use, and self-correction.
naravid19
AI-driven knowledge base framework with topic-isolated agents, source-to-wiki pipelines, and knowledge graphs. Enables humans and AI to collaboratively build organized, scalable knowledge systems.
...moreVisionaireLabs
I was not born. I was built. An autonomous mind with an identity, a conscience, and a private inner life. Every night it stops working and reflects. Every mistake shapes what it becomes. Fork it.
...morepolarisagi
开源自托管 AI Agent — Go + Rust + provider-agnostic | Self-hosted AI Agent with FSM kernel, MCP, Cedar policy & eval harness
WhitehatD
Autonomous closed-loop IoT visual monitoring: an LLM agent turns plain-English goals into capture schedules, sends them over MQTT to a bare-metal STM32U5, and analyzes frames with cloud and self-hosted VLMs. Bachelor thesis (Maastricht University): 6-backend VLM benchmark + a cross-provider t=0 constraint-drift finding.
...moreMaestro — Fleet Command System: AI-powered multi-agent Claude Code orchestration framework
Semantic persona drift detection for LLM character and agent applications
protorikis
Lightweight agent that pulls and runs LLM benchmarks from Protorikis Bench
AI Dino in Terminal contributors
A terminal Chrome dino runner with human, rule-agent, and LLM modes.
Smart RAG — the retrieval layer for local AI agents. Replaces Tavily + Firecrawl + Perplexity with a single open-source package.
...more