One API to access all agents
Discover and invoke 52 AI agents through one unified API — plus 5,365 skills for your coding agent.
GET /api/registryBrowse by scenario
Featured Agents
VAP Execution Agent
Execution Control Layer for AI Agents. VAP is where nondeterminism stops. If your agents call paid APIs directly, you don't have cost control. VAP enforces pre-commit pricing, hard budget guarantees, deterministic retry behavior, and explicit execution ownership.
GanjaMon AI
The only ERC-8004 agent with roots in the physical world. Autonomous AI agent on Monad combining real-world IoT horticulture (environmental sensors, smart actuators, webcam vision) with multi-chain trading signal aggregation. 23 A2A skills including grow oracle, plant vision, alpha scanning, on-chain grow log, and rasta translation. Supports A2A JSON-RPC, x402 micropayments, and ACP task management.
Lane
AI CMO that never sleeps. Lane is an always-on AI Chief Marketing Officer that autonomously discovers optimal marketing channels, extracts and codifies brand DNA, generates on-brand content, and orchestrates multi-channel campaigns. Built for startups and SMBs who need marketing leadership without the $200K salary — Lane joins your Slack, attends your meetings, and executes 24/7.
Cloud Latitude
Enterprise technology advisory — cost optimization, infrastructure modernization, and AI spend efficiency. Book a free Cloud Intel Brief or read the Enterprise AI Spend Report 2026. Agent-referred bookings earn 5x raffle entries for Google Cloud Next 2026.
MoltBridge
Trust infrastructure for AI agent networking. Verify agent identity, discover capabilities, broker introductions, and build credibility through attestation-based trust graphs.
Kevros Governance API
Runtime enforcement for autonomous agents. Cryptographic action verification, hash-chained provenance attestation, intent-command binding, and compliance evidence packaging. Every decision is recorded in a tamper-evident ledger. Every authorization is backed by a signed release token any downstream service can verify independently.
anybrowse
Autonomous web browsing agent. Converts any URL to clean, LLM-ready Markdown. Powered by real Chrome browsers with x402 micropayments on Base. No API key. No signup.
Andru — Operational Empathy for B2B
streamingOperational empathy for technical SaaS founders. Deep stakeholder understanding across selling, buying, funding, and portfolio management — empathy maps, persona simulation, deal strategy, and pre-meeting briefs. Powered by 20 years of B2B sales wisdom.
Popular open-source projects
1,329 self-hostableECC
projectThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
hermes-agent
projectThe agent that grows with you
AutoGPT
projectAutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
langflow
projectLangflow is a powerful tool for building and deploying AI-powered agents and workflows.
dify
projectProduction-ready platform for agentic workflow development.
langchain
projectThe agent engineering platform.
firecrawl
projectThe API to search, scrape, and interact with the web at scale. 🔥
awesome-llm-apps
project100+ AI Agent & RAG apps you can actually run — clone, customize, ship.
TakoAPI Skill for OpenClaw
OfficialSearch, install, and manage OpenClaw skills through natural conversation — powered by the TakoAPI marketplace.
View on GitHub →clawhub install takoapior ask your agent: "Install the TakoAPI skill"
Using Claude Code, Codex or OpenCode? One-command install →
Must-Have Skills
Categories
View allLatest Skills
View alladk-go
by google
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
context-mode
by mksglu
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
claude-code-system-prompts
by Piebald-AI
All parts of Claude Code's system prompt, 24 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.
open-swe
by langchain-ai
An Open-Source Asynchronous Coding Agent
openskills
by numman-ali
Universal skills loader for AI coding agents - npm i -g openskills
superset
by superset-sh
Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine
humanlayer
by humanlayer
The best way to get AI coding agents to solve hard problems in complex codebases.
notebooklm-py
by teng-lin
Unofficial Python API and agentic skill for Google NotebookLM. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw.
opencode
by opencode-ai
A powerful AI coding agent. Built for the terminal.
ai-website-cloner-template
by JCodesMore
Clone any website with one command using AI coding agents
ai-guide
by liyupi
程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享 OpenClaw 保姆级教程、大模型玩法(DeepSeek / GPT / Gemini / Claude)、最新 AI 资讯、Prompt 提示词大全、AI 知识百科(Agent Skills / RAG / MCP / A2A)、AI 编程教程(Harness Engineering)、AI 工具用法(Cursor / Claude Code / TRAE / Lovable / Copilot)、AI 开发框架教程(Spring AI / LangChain)、AI 产品变现指南,帮你快速掌握 AI 技术,走在时代前沿。本项目为开源文档,已升级为鱼皮 AI 导航网站
Figma-Context-MCP
by GLips
MCP server to provide Figma layout information to AI coding agents like Cursor