How do I test if the API is running?
Make a GET request to `https://api.valgresky.com/gres/health`. No authentication is required, and it returns `{ "Gres Check": "ok" }`.
@valgresky
基本信息
Gres is a minimalist AI command server for agents and developers. Snap pages, grab sites, source docs, and ask anything. One interface, zero fluff.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Gres API is an agentic endpoint layer built with FastAPI, offering modular tools, secure key authentication, and production-ready Docker deployment. It provides endpoints for snapping web pages, crawling sites or sitemaps, listing indexed sources, and querying a vector index via RAG (Retrieval-Augmented Generation).
Set your API key in a .env file as VALGRESKY_API_KEY=sk_valgresky_yourkeyhere. The base URL is https://api.valgresky.com. Use the health check endpoint without authentication (/gres/health). All other endpoints require an X-API-Key header. Invoke endpoints like /gres/snap, /gres/grab, /gres/source, and /gres/ask with appropriate JSON payloads.
/gres/snap/gres/grab/gres/source/gres/askMake a GET request to `https://api.valgresky.com/gres/health`. No authentication is required, and it returns `{ "Gres Check": "ok" }`.
All main API endpoints require an `X-API-Key` header. Set your key in a `.env` file as `VALGRESKY_API_KEY=sk_valgresky_yourkeyhere` and include it in every request.
Four authenticated endpoints: `/gres/snap` (snap a page), `/gres/grab` (crawl a site or sitemap), `/gres/source` (list indexed sources), and `/gres/ask` (query the vector index with RAG). Plus a public health check at `/gres/health`.
Yes. A Docker Compose file is provided that builds the service, exposes port 8051, mounts required directories, and sets environment variables like `OPENAI_API_KEY` and `GRES_EMBEDDINGS_PATH`.
The server includes a shared MCP (Model Context Protocol) instance in `/src/tools/mcp.py`. Tools like `snap` are decorated with `@mcp.tool` and can be invoked as MCP tools, enabling integration with AI agents.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
Agent conductor — AGENTS.md contract parser, SKILL.md registry, CHP decision engine over MCP

Give your AI agent the ability to see any webpage. Capture screenshots from Claude, Cursor, or any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, custom viewport, ad bloc

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
评论