Agent Marketplace

One API to access all agents. Discover and invoke AI agents through one unified API — described by open A2A AgentCards.

Paper2Poster

project

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

🧰Agent框架🔍研究检索
Paper2Poster/Paper2Posterself-host3.8k

atmosphere

project

Real-time transport layer for Java AI agents. Build once with @Agent — deliver over WebSocket, SSE, gRPC, and WebTransport/HTTP3. Talk MCP, A2A and AG-UI.

🧰Agent框架
Atmosphere/atmosphereself-host3.8k

tokscale

project

🛰️ A CLI tool for tracking token usage from OpenCode, Claude Code, 🦞OpenClaw (Clawdbot/Moltbot), Pi, Codex, Gemini, Cursor, AmpCode, Factory Droid, Kimi, and more! • 🏅Global Leaderboard + 2D/3D Contributions Graph

💻编程开发🧰Agent框架
junhoyeo/tokscaleself-host3.7k

golutra

project

Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golutra transforms Codex, Claude Code, and OpenClaw into a unified agent system with parallel execution, task orchestration, long-running workflows, and AI productivity workspace.

💻编程开发🧰Agent框架
golutra/golutraself-host3.7k

awesome-openclaw-agents

project

162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!

🧰Agent框架
mergisi/awesome-openclaw-agentsself-host3.7k

embabel-agent

project

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

🧰Agent框架
embabel/embabel-agentself-host3.7k

claude-code-book

project

《御舆:解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析,15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站:

💻编程开发🧰Agent框架
lintsinghua/claude-code-bookself-host3.7k

all-agentic-architectures

project

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

🧰Agent框架🔍研究检索
FareedKhan-dev/all-agentic-architecturesself-host3.6k

EvoScientist

project

🔬 Harness Vibe Research with Self-evolving AI Scientists

🧰Agent框架🔍研究检索
EvoScientist/EvoScientistself-host3.6k

MIRIX

project

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.

🧰Agent框架🔍研究检索
Mirix-AI/MIRIXself-host3.6k

Acontext

project

Agent Skills as a Memory Layer

🧰Agent框架
memodb-io/Acontextself-host3.5k

rlcard

project

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

🧰Agent框架
datamllab/rlcardself-host3.5k

agentic-rag-for-dummies

project

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

🔍研究检索🧰Agent框架
GiovanniPasq/agentic-rag-for-dummiesself-host3.5k

GLM-5

project

GLM-5: From Vibe Coding to Agentic Engineering

💻编程开发🧰Agent框架
zai-org/GLM-5self-host3.4k

ii-agent

project

II-Agent: a new open-source framework to build and deploy intelligent agents

🧰Agent框架
Intelligent-Internet/ii-agentself-host3.3k

basic

project

⭐⭐⭐⭐⭐ 面向 AI 编程的管理系统框架,兼容PC、移动端。AI-oriented management system framework, compatible with PC and mobile device.

💻编程开发🧰Agent框架
fantastic-admin/basicself-host3.3k

metorial

project

Connect any AI model to 1200+ integrations (MCP, CLI, API)

🧰Agent框架
metorial/metorialself-host3.3k

beeai-framework

project

Build production-ready AI agents in both Python and Typescript.

🧰Agent框架
i-am-bee/beeai-frameworkself-host3.3k

goclaw

project

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.

🧰Agent框架
nextlevelbuilder/goclawself-host3.3k

agentgateway

project

Next Generation Agentic Proxy for AI Agents and MCP servers

🧰Agent框架
agentgateway/agentgatewayself-host3.3k

qiushi-skill

project

求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done.

🧰Agent框架
HughYau/qiushi-skillself-host3.2k

ROLL

project

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

🧰Agent框架
alibaba/ROLLself-host3.2k

openai-agents-js

project

A lightweight, powerful framework for multi-agent workflows and voice agents

🧰Agent框架
openai/openai-agents-jsself-host3.2k

neo

project

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

🧰Agent框架
neomjs/neoself-host3.2k
← PrevPage 7 of 24Next →