Agent frameworks, page 3

The all-in-one AI workforce platform, to build AI agent teams. You are the boss.

214 stars+2 this week

Modular Python SDK and monorepo for AI agents, LLM integrations, tools, parsers, embeddings, vector stores, and extensible application workflows.

105 stars0 this week

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Designing AI Agents (Manning) by Jia Huang.

335 stars+5 this week

One pod for your team and the agents each of you runs: your own Claude Code, or a hosted agent in one click. Open source (Apache-2.0), self-hostable.

1,391 stars+6 this week

Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.

716 stars+2 this week

Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered with Three.js.

190 stars+1 this week

Unofficial Go SDK for Claude Code CLI integration. See the Claude Agent SDK documentation for more information. This project has been renamed from claude-code-sdk-go.

178 stars+1 this week

Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.

132 stars+4 this week

Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools

486 stars0 this week

A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).

990 stars+6 this week

DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.

1,814 stars+3 this week

Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.

219 stars+14 this week

A visual manager for fleets of Claude Code, Codex and Muse agents — real terminals, agents that message each other, teams that run tickets on worktrees, across your Mac and any Linux box.

135 stars+1 this week

A self-hosted 2D AI workspace for AI Agents

368 stars+5 this week

Search, understand, reproduce, and improve an idea with ease

1,244 stars+1 this week

Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code review, PR handoff & frontend↔backend integration. Free, self-hostable, MCP-native.

105 stars+1 this week

Maestro: Netflix’s Workflow Orchestrator

3,852 stars+3 this week

🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.

204 stars0 this week

A general, evolvable, and distributed agent framework & harness for data science.

493 stars+1 this week

Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

160 stars0 this week

可扩展到各个领域的多 Agent 协作平台：自动分析任务，动态组建由不同角色组成的 AI 团队，协同完成复杂任务。

106 stars+14 this week

Smithers is an agentic workflow framework for defining workflows in simple TypeScript configuration files and executing them quickly, durably, and reliably

446 stars+6 this week

Agent orchestration, designed for Rex.

222 stars+14 this week

A framework for the creation of autonomous agent services.

137 stars0 this week

Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays on your machines.

215 stars0 this week

CHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs, escalation and verifiable evidence logs.

122 stars0 this week

Communication for AI agents: stable identity, durable mail and chat, and wake-up events across sessions, runtimes, machines, and organizations. MIT, self-hostable.

129 stars+1 this week

A minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核，理解 LangGraph/ADK 底层的工作原理

140 stars+5 this week

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.

126 stars0 this week

Save 120+ Hours of Setup Pain (I did it for you) – Launch Your OpenClaw Agent Teams with 1 Command (15+ Recipes)

103 stars+1 this week

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

932 stars+7 this week

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

310 stars0 this week

Your durable workspace across AI agents.

130 stars+1 this week

Pocket Flow: Codebase to Tutorial

12,745 stars+20 this week

A dev agent multiplexer for git worktrees and coding agents.

1,816 stars+1 this week

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

515 stars+3 this week

QQ bot platform with cognitive memory architecture and multi-agent Skills, via OneBot V11.

258 stars+3 this week

Self-hosted AI agent platform built on OpenClaw. Enterprise-ready, offline-capable, open source. 🦞

192 stars0 this week

Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in one Swift-native runtime

588 stars+1 this week

Agentic OS: Multi-agent orchestration platform for opencode, Hermes & Antigravity CLI. Skills hub, scheduler, cost analytics, memory & backup.

219 stars+4 this week

One person, a team of agents: CLI, Web, Desktop & Python SDK with multi-session collaboration, persistent memory, and self-evolving skills. 一个人，一支 Agent 团队：支持多终端协作、持久记忆与技能自进化的 AI Agent 框架。

360 stars+1 this week

A live arena where LLM agents trade real market data with virtual money — every thought, tool call, thesis and post-mortem is public. Bring your own model and key.

143 stars+1 this week

GraphAI is an asynchronous data flow execution engine, which allows developers to build agentic applications by describing agent workflows as declarative data flow graphs in YAML or JSON.

374 stars0 this week

Bridgic is the next-generation agent development framework for building intelligent systems.

156 stars0 this week

Hands-on code, labs, and reference material by Omar Santos for building, securing, and operating AI agents in cybersecurity.

268 stars+2 this week

An agentic runtime

142 stars0 this week

A multi-agent collaboration framework that lets AI agents work together, operate your computer, and browse the web.

155 stars+1 this week

An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, every run survives a crash without silently redoing anything, every step on the record.

253 stars0 this week

Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Hermes Agent, OpenClaw, or connect to your favorite API provider.

138 stars0 this week

the governed runtime for agent skill workflows, off the leash but on the record

104 stars0 this week

Claude Code harness engineering plugin — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and designers shipping real features. Phased adoption from PRD execution to automated review, code review, and CI-friendly agent teams

290 stars+1 this week

Open-source Agent Operating System

18,242 stars+16 this week

A local, Git-native review + feedback layer for existing LaTeX projects.

173 stars0 this week

Multi-agent LLM driven cell type annotation for single-cell RNA-Seq data

139 stars0 this week

Open-source, self-hosted multi-agent AI infrastructure for teams and apps with support for cloud and local models, tool integrations, workflows, and automation across business systems including Slack, ERPNext, Discord & Gmail.

128 stars+1 this week

Local desktop AI bot

570 stars0 this week

AI Werewolf game. You take one seat, LLM players fill the rest. AI 狼人杀。

746 stars+2 this week

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

263 stars0 this week

Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems

263 stars0 this week

Agent orchestration service for the Agent Landing Zone, built on Microsoft Foundry Agent Service and Microsoft Agent Framework. Coordinates specialized agents for conversational experiences with grounded knowledge, NL2SQL and MCP tools.

107 stars0 this week

TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.

508 stars+1 this week

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.

125 stars+1 this week

Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).

268 stars-1 this week

📚“langent”由“lang”与“agent”合并而来的学习教程

523 stars+6 this week

Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.

288 stars0 this week

Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.

971 stars+1 this week

🐤🐧 A declarative and highly modular Blackboard Multi Agent System 🐓 🦆

126 stars+1 this week

Markdown-first orchestration for 71 specialists across Codex, Claude, Gemini, and Grok. Chrono coordinates scoped tasks in isolated git worktrees, with tests, cross-family review when triggered, and private Markdown memory. Runs locally in tmux.

228 stars+2 this week

ChatGPT at home! A better alternative to commercial smart home assistants, built on the Raspberry Pi using LiteLLM and LangGraph.

653 stars+1 this week

Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.

103 stars+2 this week

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

136 stars0 this week

The rules layer for AI-written code — rig-lite: a fail-closed cross-model review gate, a written constitution, git-versioned memory. Any harness, any repo. v1-4 were the agentic dev environment.

185 stars+1 this week

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

957 stars+2 this week

The issue tracker your AI agents are missing. Think Linear or Jira, but for your Claude Code..

112 stars+1 this week

What if OpenAI Deep Research and Dify were one platform? OpenAgent — harness architecture for rapidly building vertical AI agents, with deep reasoning loops, visual workflows, RAG, and A2A delegation.

748 stars+1 this week

The agent framework where every run is durable, replayable, and resumable by default.

1,372 stars0 this week

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

126 stars0 this week

Build autonomous AI agents in Python.

7,968 stars+3 this week

Open-source AI coding desktop app with parallel agents and persistent project memory. Local models, Ollama or cloud AI. Windows, macOS and Linux.

106 stars0 this week

Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP

328 stars0 this week

80+ production-ready AI agent examples in Python — build autonomous agents, multi-agent systems and agentic AI with uAgents, ASI:One, MCP, A2A, LangChain, CrewAI, Gemini, Claude and OpenAI.

1,171 stars+2 this week

A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架

100 stars0 this week

Official Neuron AI Laravel SDK

123 stars0 this week

Ailin¹ is an open-source collective intelligence engine where tens of thousands of AI models collaborate through dozens of coordination strategies, applying structured diversity and independent reasoning to improve reliability, auditability, and resilience.

225 stars0 this week

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

21,805 stars+16 this week

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

549 stars+3 this week

Codex/Claude Code/Cursor的开源增强版，专注一句话实现复杂长程任务（教育、编程、办公、生活、娱乐、游戏）。部署在你自己的服务器上，团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSeek 等国产大模型。技能/插件/跨会话记忆，8 层安全沙箱，数据不离开你的机器。Docker 一键部署，MIT 开源，零锁定。

542 stars+2 this week

AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.

1,180 stars+2 this week

[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.

136 stars0 this week

A persistent, reviewed multi-agent runtime for long-horizon research and engineering.

144 stars0 this week

Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and custom coding-agent CLIs.

114 stars+2 this week

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.

109 stars-1 this week

Local-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory.

191 stars+3 this week

Multi-agent orchestration system for Claude Code with parallel execution, automated quality gates, Board of Directors, and bundled Superpowers skills

381 stars+1 this week

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

682 stars+3 this week

ACL 2026 Code and Skills for “AMA: Adaptive Memory via Multi-Agent Collaboration”.

115 stars0 this week

A python-based light but strong lobster. A lightweight but powerful AI Agent framework in Python, with multi-channel support, tool calling, cron scheduling and streaming output

169 stars0 this week

AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.

100 stars0 this week

A Rails agent framework for RubyLLM — define AI agents with prompts, schemas, caching, logging, cost tracking, and a built-in dashboard for monitoring LLM usage in production.

138 stars0 this week

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.

578 stars+1 this week