🐙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。

herdr

项目

the runtime your coding agents live on

💻编程与开发
herdrdev/herdr自托管38.6k

ai-agent-book

项目

《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

🧰智能体框架💻编程与开发
bojieli/ai-agent-book自托管47.2k

dokploy

项目

Open Source Alternative to Vercel, Netlify and Heroku.

☁️DevOps 与自动化🧩后端
Dokploy/dokploy自托管37.3k

shannon

项目

Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

KeygraphHQ/shannon自托管46.7k

graphify

项目

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

💻编程与开发🧰智能体框架
Graphify-Labs/graphify自托管116.8k

dashi-ppt-skill

项目

An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.

📑演示与文档🔍研究与搜索
chuspeeism/dashi-ppt-skill自托管8.2k

astrid

项目

Astrid is a portable, capability-secure operating system for composable software.

🧰智能体框架
astrid-runtime/astrid自托管10.3k

autoharness

项目

Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

💻编程与开发🔍研究与搜索
tigerless-labs/autoharness自托管4.9k

graphjin

项目

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

🧩后端🧰智能体框架
dosco/graphjin自托管3.1k

open-managed-agents

项目

Open-source Claude Managed Agents API implementation and self-hosted Claude Tag-style agent runtime. Drop-in compatible; runs on Cloudflare Workers/Durable Objects or Node.js. Apache 2.0.

🧰智能体框架☁️DevOps 与自动化
openma-ai/open-managed-agents自托管224

caura-memclaw

项目

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.

🧰智能体框架🔍研究与搜索
caura-ai/caura-memclaw自托管430

Foundry

项目

Transform any idea into a running AI-powered company

🎨前端🧰智能体框架
axislab-top/Foundry自托管473

ai-job-search

项目

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

💻编程与开发🧰智能体框架
MadsLorentzen/ai-job-search自托管42.8k

kitaru

项目

Record, replay, and improve AI agents in production, built on ZenML

🧰智能体框架☁️DevOps 与自动化
zenml-io/kitaru自托管235

muxi

项目

Deploy intelligence. Open-source infrastructure for AI agents in production.

🧰智能体框架☁️DevOps 与自动化
muxi-ai/muxi自托管210

skills

项目

Agentic Development skills behind the JS Mastery workflow

🧰智能体框架
jsmastery-pro/skills自托管1k

astrid

项目

Unicity Astrid OS: a secure operating system for AI agents.

🧰智能体框架
unicity-astrid/astrid自托管10.3k

mindshub

项目

The unified workspace where open-source models get things done for you.

💻编程与开发🧰智能体框架
mindsdb/mindshub自托管39.7k

LSF_MDia

项目

[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.

🧰智能体框架
pzqpzq/LSF_MDia自托管425

repobrain

项目

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

💻编程与开发🧰智能体框架
study8677/repobrain自托管1.3k

agentic-awesome-skills

项目

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,115+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

💻编程与开发🧰智能体框架
sickn33/agentic-awesome-skills自托管46.4k

burner-agents

项目

A swarm of disposable agents for unattributable web interaction. The user never acts on the web directly, delegating instead to agents that are destroyed on completion, leaving nothing that leads back.

🧰智能体框架🔍研究与搜索
TimFryAI/burner-agents自托管646

SuperNovaAgent

项目

SuperNova is a Windows-first desktop AI Workbench that turns chat into traceable tasks. It combines a Tauri + React Workbench, Rust Product Runtime, typed protocol, and Process Kernel so actions can produce visible artifacts, runtime receipts, replayable evidence, and controlled workspace execution.

🎨前端🧰智能体框架
Ray-Code-Svg/SuperNovaAgent自托管209

nasiko

项目

Developer Control Plane for your AI Agents

🧰智能体框架
Nasiko-Labs/nasiko自托管6.6k