Automatically detects git repositories to namespace and isolate memories per-repo, with cross-repo memory support and automatic repository indexing for semantic code search.

Supports repository-based memory management with automatic detection and indexing of GitHub repositories for context-aware semantic search and code navigation.

Provides hosted deployment storage backend using PostgreSQL with pgvector extension for vector embeddings, semantic search, and team sharing of memories.

Distributed as a Python package on PyPI for installation and deployment of the ContextFS memory layer.

Default local storage backend using SQLite with FTS5 for keyword search, memory storage, and session management.

1. Click on "Install Server".

2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.

3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ContextFS search for recent decisions about database architecture"

That's it! The server will respond to your query, and you can continue using it as needed.

Here is a step-by-step guide with screenshots.