@angrysky56
基本信息
An intelligent code memory system that leverages vector embeddings, structured databases, and knowledge graphs to store, retrieve, and analyze code patterns with semantic search capabilities, quality metrics, and relationship modeling. Designed to enhance programming workflows th
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。
Coder DB is a structured memory system for AI assistants, specifically designed to enhance coding capabilities by integrating multiple database types (Qdrant vector database, SQLite, and a knowledge graph) via the Model Context Protocol (MCP) with Claude Desktop.
Install dependencies using Poetry, configure environment variables in a .env file (e.g., Qdrant host, port, API key, SQLite database path), and run the FastAPI MCP server. Store code memories using the qdrant-store-memory command and retrieve them with qdrant-find-memories. Query the SQLite algorithm database via SQL or explore the knowledge graph for relationships.
It uses Qdrant (vector database), SQLite (relational database), and a knowledge graph. Data is stored locally in Qdrant and SQLite database files; the knowledge graph is also version-controlled.
Requires Python, Poetry, FastAPI, Uvicorn, Qdrant client, SQLite (via aiosqlite), and other dependencies listed in `pyproject.toml`. Install with `poetry install --with dev`.
Store with `qdrant-store-memory(json.dumps({...}))` and retrieve with `qdrant-find-memories("query")`. Provide metadata like language, complexity, tags, and quality metrics.
The MCP server is a FastAPI application that exposes standardized endpoints for AI models (via Claude Desktop) to interact with the memory system. It runs on HTTP and supports health, memory, and algorithm endpoints.
Role-based access for sensitive code, optional Qdrant API key (set in `.env` as `QDRANT_API_KEY`), and code sanitization to remove sensitive data before storage.
Model Context Protocol Servers
The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your
Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab
Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
评论