#48 · Primary category： AI Gateway & API Infrastructure
executor
The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure environment.
Project last updated：08/30/26
GitHub Stars
3.4K
Forks
266
Contributors
63
License
MIT
Why we included this project
When a team uses several AI assistants, each one usually ends up with its own copy of the same API keys and tool configs. Executor fixes that by sitting between agents and your services: you register an integration once (OpenAPI, GraphQL, MCP, or custom JavaScript), attach credentials, and set per-tool policies. Any MCP-compatible client, from Claude Code to Cursor to ChatGPT, then uses the same catalog, so setup isn't repeated and permissions stay in one place. It can run as a CLI, desktop app, hosted cloud, or self-hosted on Docker or Cloudflare, which makes it easy to start small and move to a managed endpoint later. That's a solid choice for developers wiring LLM assistants to real third-party APIs without losing control over auth and access rules.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OmniRoute
Open-source AI gateway: one endpoint, 290+ providers (90+ free), 500+ models, auto-fallback, token compression, MCP/A2A, works with Claude Code, Codex, Cursor, Cline, Copilot.
CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude model through API
kong
🦍 The API and AI Gateway
novu
The open-source communication infrastructure for agents and products
GPT_API_free
Free API for large models, supports GPT, DeepSeek, etc., 10k free points daily, paid plans at 10-20% of official price.