Open-Source AI Agents DirectoryOpen-Source AI Agents Directory

Deep Research Agent

Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search

Deepsearch Academic

An implementation of Google Deep Search with support for 1000+ references, local inference, chatting with your scraping session using RAPTOR, and report generation.

Weaver

基于 LangGraph 的企业级 AI 智能体平台，支持深度研究、代码执行 ，并提供 62+ 内置工具与类Manus的多 Agent 配置。支持 SSE 实时流、任务取消、记忆管理以及多模态交互等能力

Iterative Development

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

BrowserPilot

Open‑source alternative to Perplexity Comet, director.ai and firecrawl combined

Pi Rust

Rust-native, library-first coding-agent runtime and terminal CLI inspired by Pi, with composable LLM providers, tools, sessions, and plugin ABI

Bello

3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in parallel, have them check each other’s work, and reduce unnecessary model calls and noisy tool output. Turn on only what you need.

Tubecli

⚡ TubeCLI — The Ultimate Open Source AI Agents Ecosystem | Agents Browser · Agents Workflow · Agents Studio World

Spotter

Official codebase for Spotter: Let the Embodied Model Lead, and the VLM Reflect for It

Deepresearch Agent

一个生产级的深度研究 Agent 系统，从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力，配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。

Dark Factory Experiment

A repository that ships its own code. AI workflows triage issues, implement them, review, and auto-merge with no human reading the diff. Runs on Archon. The app it maintains is a cited RAG chat over YouTube transcripts, live at chat.dynamous.ai.

Fastbrowse

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

Value

⚡ "Value" - https://value.valmi.io . Valmi Value is Outcome-based billing and payments infrastructure for AI agents. Meter usage, configure flexible pricing, and track costs & profitability - so you can focus on building great AI products.

AISquare Studio QA

Setting up QA testing agents using playwright and crewAI

AI Ppt Generator

2026 年编程导航 AI 编程实战新项目，基于 Python FastAPI + LangChain + LangGraph + React 的 AI PPT 生成器，支持主题 / 长文本 / 文档多入口生成、可编辑大纲、异步并发页面生成、在线编辑器、多主题切换、原生可编辑 PPTX 导出。覆盖 LangChain 框架实战、LangGraph 自纠环工作流、ARQ + Redis 异步任务编排、SSE 实时进度推送、PPTX 原生渲染、FontTools 溢出检测。用一套教程掌握 AI 编程全流程，从模型调用到产品交付，不到一周学完，给你的简历增加竞争力

Sample Autonomous Cloud Coding Agents

Autonomous background coding agents on AWS. Turn tasks into pull requests via isolated runtimes, with built-in orchestration, observability, and governance.

Oreilly Retrieval Augmented Gen AI

See how to augment LLMs with real-time data for dynamic, context-aware apps - Rag + Agents + GraphRAG.

Collaborative Gym

Framework and toolkits for building and evaluating collaborative agents that can work together with humans.

ConcoLLMic

ConcoLLMic: the first language- and theory-agonistic concolic execution engine via LLM agents

Basjoo

Self-hosted AI customer-support platform — per-KB RAG on Qdrant, 13 LLM providers, SSE streaming, embeddable chat widget. FastAPI + Vite + SQLite, all in Docker Compose.

GAAI Framework

Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

Benchmark

Open benchmarks for browser agents: BU Bench V2.1, 200 real web tasks. Rerun them with your own API keys.

OmicsClaw

Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper.

Self Improving Agents

Self-Improving Agents -- A Progression Four levels of self-improving code agents, from the simplest loop to a full adversarial arena with self-modifying agents. Each level adds one key idea.