Open-Source AI Agents DirectoryOpen-Source AI Agents Directory

Rulora

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.

Loop Js

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Goal Flow

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to runnable code, swap wire protocols (Dify/OpenAI).

Gen Mentor

[WWW '25 Oral - GenMentor] Official code of our paper "LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System", accepted by WWW 2025 (Industry Track) as an Oral Presentation.

Wechat Mac Rpa

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

Aside Codemode

One call where Aside used to spend fifty — rg-backed search, Aside-shaped file tools, and batched browser work inside a single sandboxed JavaScript block. On a real folder, 55s of find+grep became 1s.

Stock Analyst

The agent behind VYNN AI, a personal AI financial analyst with 5K+ users. Ask any market question; code computes every number and every claim is sourced.

Gozar

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

Customer Service AI Agent

使用LangGraph搭建多智能体客服系统

Pentestkit

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104 (100%) on the XBOW validation benchmarks, powered by Kimi K3.

Loopgain

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of running to a fixed max_iterations cap. Real-time loop-gain (Aβ) bands + best-so-far rollback. Adapters for LangGraph, CrewAI, AutoGen, LangChain, OpenAI Agents, and Claude Agent SDK; raw API for custom stacks.

ObsidianRAG

Ask questions about your Obsidian notes using local AI. Privacy-first RAG with Ollama, LM Studio, or any OpenAI-compatible server. Obsidian plugin + Docker + PyPI.

Trackinizer

Epistemological database for agent and human efforts, beliefs, and findings.

Tokenjam

Token Efficiency For AI Agents

Fluent

Fluent is a self-improving software factory. It autonomously turns your team's vision, ideas, bug reports, user feedback, production logs, and agent traces into working software.

Anaxa

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

Reels Af

Automate viral reel/tik-tok videos via AI multi-agent system. ~$0.1/reel.

Docling Rs

Full Rust port of Python docling

Hands On LLM

动手学大模型全栈：CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地（含真实实验、曲线与复现脚本）

OpenHarness

Reliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.

Nagato AI

Simple cross-LLM AI Agent library

ForgeDock

ForgeDock — autonomous AI dev pipeline for Claude Code. GitHub as agent memory: issue in, PR out.

AlgoTune

AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.

Dsh Auto Memory

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.