Agent frameworks

Build and run agents you can see, understand and trust.

35,652 stars+404 this week

A smarter, self-hosted AI assistant — multi-user, multi-agent.

11,798 stars+312 this week

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

11,294 stars+117 this week

Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.

968 stars+43 this week

The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

6,121 stars+141 this week

SRE Agent - CNCF Sandbox Project

3,824 stars+65 this week

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

9,084 stars+52 this week

Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions

1,532 stars+30 this week

A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。

3,936 stars+43 this week

Your Company Agentic Operating System

1,030 stars+42 this week

The open-source app everyone uses to manage agents at work

112,415 stars+1,880 this week

Sub-50mb agentic, voice and vision intelligence for consumer devices.

14,603 stars+184 this week

Connect any AI copilot or autonomous agent to your enterprise tools — through a single, secure MCP/Agent gateway with built-in identity, access control, and full observability.

3,866 stars+107 this week

Event-stream AI Agent framework for building your persona bot 🍊

344 stars+20 this week

A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse.

894 stars+13 this week

A self-evolved, sovereign desktop AI agent built for real-world action — beyond model wrappers and coding copilots. / 真实实践中自我演化的独立桌面 AI Agent。

699 stars+49 this week

Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, fully end-to-end encrypted

2,181 stars+62 this week

🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

5,436 stars+7 this week

Build resilient agents.

44,674 stars+328 this week

100% free, open-source personal agents for your messaging apps, tools, and services

496 stars+66 this week

面向企业的数字员工构建与运行平台：把专业员工的经验、流程与判断标准，固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。

828 stars+55 this week

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

26,944 stars+38 this week

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

68,092 stars+250 this week

The agent engineering platform.

149,240 stars+387 this week

Your lightweight open-source personal agent.

49,949 stars+193 this week

SuperARIS — Your personal research agent with ARIS (Auto Research In Sleep), powered by a team of agents.

47 starsThis week: Not stated

Supervised agent runtime for Rust: compose LLM calls into pipelines that cancel, isolate panics, retry, budget and resume.

12 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

55 starsThis week: Not stated

Aurora — Open source AI-powered agentic incident management & root cause analysis for SREs. LangGraph agents investigate across AWS, Azure, GCP, Kubernetes. Integrates with PagerDuty, Datadog, Grafana, Slack and More. Apache 2.0.

457 starsThis week: Not stated

Building a Mixture of Agents system for DeepSeek Harness: persistent agents, shared knowledge, direct communication and independent review.

28 stars+26 this week

Frontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released.

63 stars+49 this week

An end-to-end framework for Agentic Reinforcement Learning.

164 stars+70 this week

the extensible, customizable, self-documenting, real-time multi-agent computing environment

129 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

一个会主动发现任务的智能体

235 stars+59 this week

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

53 starsThis week: Not stated

Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.

272 stars+39 this week

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

53 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

1,444 starsThis week: Not stated

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

54 starsThis week: Not stated

LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.

1,515 stars+18 this week

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

635 stars+51 this week

CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.

1,140 stars+85 this week

Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.

750 stars+20 this week

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

1,124 stars+8 this week

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

232 stars+36 this week

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

22,154 stars+74 this week

A local-first inbox for long-running AI agents, built with DeepAgents and LangGraph.

545 stars+9 this week

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

85,163 stars+283 this week

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

1,915 stars+19 this week

The self-driving agent platform

43,112 stars+94 this week

可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

7,632 stars+57 this week

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.

3,341 stars+18 this week

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

6,169 stars+46 this week

You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub/Kiro/Z.AI/Xiaomi/MiniMax/Kimi(300+ models, 200+ LLM providers, free models no auth) Build your AI company with multiple teams

2,449 stars+63 this week

Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent，免 Root 免 Termux

499 stars+47 this week

A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时：快速开发、验证和恢复复杂 AI 工作流，并将其稳定交付为服务。

966 stars+13 this week

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

420 stars+10 this week

A Python framework for modular, self-contained skill management for machines.

180 stars+11 this week

🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队，几分钟交付完整方案；验收自动核验，网页 / 桌面 / Docker 全渠道。

2,458 stars+27 this week

A playground for neuro-san

1,195 stars+2 this week

The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力，并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。

368 stars+138 this week

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, routines, gateway.

144 stars+23 this week

High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.

20,053 stars+8 this week

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

5,196 stars+27 this week

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

8,953 stars+32 this week

The open-source agentic framework to build, orchestrate, and operate production AI agents.

150 stars+1 this week

Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision in herdr.

220 stars+5 this week

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).

1,029 stars+111 this week

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

81,304 stars+658 this week

📊 电商数仓智能问数 AI Agent，最适合用于系统学习 LangGraph 的实战项目：基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React，完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL 执行与流式查询展示。前后端完整代码全栈可跑，Docker 环境一键部署，配套 ai-agents-from-zero 免费教程与章节代码分支。适合系统学习大模型应用、数据分析 Agent 和企业级 AI 工程落地。

518 stars+17 this week

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

742 stars+7 this week

Run coding agents like infrastructure, not terminal sessions. Warren manages isolation, lifecycle, spend, recovery, and Git delivery on compute you control.

514 stars+2 this week

A programmable tool and agent runtime for Pi

328 stars+6 this week

Multi-Agent Collaboration for Team and Friends

1,494 stars+16 this week

Mission control for AI coding agents. Watch Claude Code, Codex, Gemini and a dozen more work live in one macOS terminal: live status, an editor that follows their edits, undo for any turn, approvals from your phone and local models. 20+ built-in tools, all on the site below. Built on Ghostty.

141 stars+5 this week

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

5,053 stars+14 this week

不是问答机器人，而是能真正干活的数字分身。共享智能体，共享项目上下文，让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中

861 stars+56 this week

Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.

47,847 stars+106 this week

Python trading framework with AI agents that actually place the trade. Backtest, paper and live trade on 12 brokers: stocks, options, futures, forex, crypto and prediction markets.

2,218 stars+19 this week

ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.

4,516 stars+21 this week

Trigger.dev – build and deploy durable AI agents and workflows

16,734 stars+42 this week

An autonomous agent that conducts deep research on any data using any LLM providers

30,591 stars+142 this week

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

31,097 stars+39 this week

Private AI agents for highly regulated teams, and for anyone who wants AI on their own computer. Open-source Python agent framework that runs fully offline.

9,327 stars+12 this week

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

10,933 stars+25 this week

An agentic framework that helps developers build resilient agentic systems

235 stars+1 this week

Run a hive mind of agents to focus on a specific goal

330 stars+7 this week

clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open the work, and pace themselves on each account's real 5-hour and weekly usage. Steer it from the Claude app.

219 stars+3 this week

Teams-first Multi-agent orchestration for Claude Code

40,702 stars+183 this week

Where people and agents build in tune.

3,900 stars+18 this week

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

1,773 stars+10 this week

The lightweight framework for building agents

700 stars+6 this week

Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

4,550 stars+6 this week

MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute

1,073 stars+6 this week

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

7,052 stars+11 this week

ReachAI企业级智能体开发平台：快速、安全完成已有业务系统智能化改造，让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise systems, enabling AI to query data, fill out forms, and execute business tasks directly within OA, ERP, CRM, and other business applications.

1,045 stars+16 this week

Brigade — Your personal intelligence, built enterprise-grade

11,370 stars+8 this week

Open-source, self-hosted, extensible Agent platform built around ReAct and Harness engineering, with AI customer support as its first complete reference application.

197 stars+28 this week

EMNLP 2026 Main Conference Paper: MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems (https://aclanthology.org/2026.emnlp-main.878/))

804 stars+14 this week

Bub it. Build it. A tiny agent runtime, composable with plugins.

1,699 stars+4 this week

AI coworker with memory and collaboration

18,146 stars+26 this week

Agent Orchestration Command Center

3,558 stars+30 this week

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

552 stars+9 this week

An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

1,471 stars+5 this week

Hermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini. Terminal, Discord, dashboard.

190 stars+11 this week

The open standard for agent coordination

385 stars+8 this week

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that interact with your data and UI.

2,169 stars+6 this week

A local-first multi-agent app development platform, built on PenguinHarness

160 stars+11 this week

Workflow orchestration framework for your product, open source: a white-label React workflow builder, durable execution on your own Temporal, human approval steps for AI agents, and a live view of every run.

438 stars+12 this week

AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.

412 stars+2 this week

Make your computer a home for your AI partner. Avibe is the local-first Agent OS: Vibey, its built-in AI partner, works out of the box, and Claude Code, Codex & OpenCode run unchanged beside it — reach them from your browser, phone, or any chat app.

639 stars+3 this week

Desktop AI agent that hires a specialist for each task, works in your real apps for weeks, and takes orders from your phone. Free, Apache-2.0.

1,447 stars-9 this week

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts. Cloud LLMs or fully local.

376 stars+4 this week

Harness LLMs with Multi-Agent Programming

4,127 stars+3 this week

A multi-agent research system for the humanities and social sciences.

249 stars+8 this week

AI multi-agent tool that turns research papers into cited commercialization and tech-transfer assessments: TRL, patent landscape, market and risks. CrewAI + FastAPI, with a reproducible benchmark.

809 stars+3 this week

[NeurIPS'26] Official Implementation for AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent(https://arxiv.org/abs/2602.03955)

278 stars+6 this week

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

8,918 stars+15 this week

Agent samples built using the Strands Agents SDK.

928 stars+4 this week

An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

1,767 stars+5 this week

Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

1,911 stars+166 this week

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done. From a laptop to a Cloudflare Worker.

369 stars+2 this week

HunterCode · Community Edition · 腾讯 WorkBuddy 金融版的开源本地替代方案 · open-source, local alternative to Tencent WorkBuddy Finance Edition · 多智能体投研终端 A股/港股/美股 · 推理在你机器上跑 · 仓位不出你硬盘 · BYOK · Apache 2.0 · docker compose 自托管

608 stars+32 this week

Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together.

979 stars0 this week

Build durable, autonomous, resilient and observable AI agents with built-in workflow orchestration, security, statefulness and telemetry.

772 stars+1 this week

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

4,470 stars+4 this week

Govern, Observe, Direct - a real-time control room for agent societies

1,271 stars+13 this week

Open-source agent for the terminal written in Rust. Use any provider or model. Issues & PRs always welcome

41,158 stars+35 this week

China Unicom's Yuanjing Wanwu Agent Platform is an enterprise-grade, multi-tenant AI agent development platform. It helps users build applications such as intelligent agents, workflows, and rag, and also supports model management. The platform features a developer-friendly license, and we welcome all developers to build upon the platform.

2,386 stars+5 this week

An open-source studio for teams of AI agents, from marketing squads to dev teams to research crews. Deploy a team, then watch them delegate and collaborate live. Self-hosted, one command.

168 stars+87 this week

Ever® Works™ - The Workshop for AI. An open agentic runtime that autonomously researches, ships, and maintains entire businesses, 24/7 - https://ever.works

192 stars+5 this week

A custom Agent OS built to be hackable, heavily inspired by OpenClaw.

441 stars+1 this week

Agentic and LLM Programming in Scala

279 stars+3 this week

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

641 stars+3 this week

Automated Penetration Testing Agentic Framework Powered by Large Language Models

16,333 stars+122 this week

Optimizing inference proxy for LLMs

4,340 stars+5 this week

Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.

1,053 stars+4 this week

Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results

139 stars+3 this week

Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.

110 stars+15 this week