🐙TakoAPI

智能体市场

一个 API,访问所有智能体。 通过一个统一 API 发现并调用 AI 智能体——以开放的 A2A AgentCard 描述。

agentshield

项目

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

🧰智能体框架
affaan-m/agentshield自托管864

agentsys

项目

AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

💻编程与开发🗂️效率与助手
agent-sh/agentsys自托管985

metabot

项目

构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code(双引擎,两家原生订阅直接用),共享记忆、Agent 工厂、定时任务、通信总线。

💻编程与开发🧰智能体框架
xvirobotics/metabot自托管968

xpander.ai

项目

xpander.ai is the runtime and control plane to build, run, and ship reliable AI agents fast and anywhere

🧰智能体框架
xpander-ai/xpander.ai自托管871

WindowsAgentArena

项目

Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

🔍研究与搜索🧰智能体框架
microsoft/WindowsAgentArena自托管898

reaper

项目

Live validation proxy tool for testing web app vulnerabilities

🎨前端🧰智能体框架
ghostsecurity/reaper自托管886

aiflowy

项目

AIFlowy is an enterprise-grade AI application development platform based on Java, comparable to products like Dify and Coze.

aiflowy/aiflowy自托管869

learn-modern-ai-python

项目

Learn Modern AI Assisted Python with Type Hints

panaversity/learn-modern-ai-python自托管872

x-tweet-fetcher

项目

Fetch X/Twitter tweets, replies, timelines, and articles without login or API keys — field tool for AI agents.

ythx-101/x-tweet-fetcher自托管872

WorldSeed

项目

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

🧰智能体框架
AIScientists-Dev/WorldSeed自托管814

spec_driven_develop

项目

Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.

💻编程与开发
zhu1090093659/spec_driven_develop自托管898

memind

项目

Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.

🧰智能体框架
openmemind/memind自托管899

Multi-Agent-Medical-Assistant

项目

⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.

🧰智能体框架💬客户支持
souvikmajumder26/Multi-Agent-Medical-Assistant自托管903

magic-context

项目

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

💻编程与开发🧰智能体框架
cortexkit/magic-context自托管2.1k

cccc

项目

Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your phone. One pip install, zero infrastructure. A production‑minded orchestrator for 24/7 workflow

💻编程与开发🧰智能体框架
ChesterRa/cccc自托管1.2k

PokeClaw

项目

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

agents-io/PokeClaw自托管910

claude-code-source-code

项目

Claude code source code

💻编程与开发
777genius/claude-code-source-code自托管915

Mava

项目

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

🧰智能体框架🔍研究与搜索
instadeepai/Mava自托管935

maro

项目

Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.

🧰智能体框架☁️DevOps 与自动化
microsoft/maro自托管921

AgileRL

项目

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.

🧰智能体框架
AgileRL/AgileRL自托管944

matcha

项目

A beautiful and functional email client for your terminal, built with Go and the charming Bubble Tea TUI library. Never leave your command line to check your inbox or send an email again!

floatpane/matcha自托管955

VibeSearchBench

项目

🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.

🔍研究与搜索
VibeBench/VibeSearchBench自托管928

WriteHERE

项目

An Open-Source AI Writing Project.

🧰智能体框架🔍研究与搜索
principia-ai/WriteHERE自托管977

chatgpt-cli

项目

ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports OpenAI, Azure, Perplexity, LLaMA, and more, with features like streaming, interactive chat, prompt files, image/audio I/O, MCP tool calls, and an experimental agent mode for safe, multi-step automation.

🧰智能体框架🔍研究与搜索
kardolus/chatgpt-cli自托管934