@elementalcollision
Basic information
AI-assisted development MCP providing long-term, on-device "AI memory" for IDEs. Powered by Kuzu GraphDB and exposed via MCP server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"GraphMemory-IDE": {
"command": "docker",
"args": [
"compose",
"up",
"-d"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
GraphMemory-IDE is an AI-assisted, long-term memory MCP (Model Context Protocol) server for IDEs, powered by the Kuzu graph database. It provides semantic vector search, graph-based knowledge storage, and real-time analytics, integrating with VSCode, Cursor, and Windsurf through dedicated plugins.
Deploy with Docker (recommended): clone the repository, navigate to docker/, and run docker compose up -d. For local development, install dependencies with pip install -r requirements.txt, start the FastAPI server with uvicorn server.main:app --host 0.0.0.0 --port 8080 --reload, and optionally launch the Streamlit dashboard separately. Required environment variables include JWT_SECRET_KEY, DATABASE_URL, REDIS_URL, and KUZU_DB_PATH.
GraphMemory-IDE is a dedicated MCP server that combines a Kuzu graph database with semantic vector search, optional Codon-accelerated graph algorithms, and real-time analytics dashboards. It is designed specifically for IDE integration and offers multi-plugin support out of the box.
Python 3.11 or higher, with dependencies in `requirements.txt`. Codon is optional but recommended for high-performance graph algorithms; if not compiled, all operations fall back to NetworkX and numpy. Docker Compose is available for production deployment with PostgreSQL, Redis, Prometheus, and Grafana.
Graph data is stored in a Kuzu database at the path specified by `KUZU_DB_PATH` (default `./data/kuzu`). Relational data and sessions are stored in PostgreSQL (default SQLite) and Redis cache respectively.
Yes, the FastAPI server uses JWT authentication with EdDSA/Ed25519 signing. A `JWT_SECRET_KEY` environment variable must be configured.
Codon acceleration requires manual compilation of native libraries via `./scripts/build_codon.sh` and is only beneficial for graphs larger than 100 nodes (configurable). The system is designed for IDE-integrated use; direct API access is available but intended for plugin and dashboard communication.
Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
Kaiva Bridge turns your API, database or documents into a managed MCP server for Claude, ChatGPT, Cursor and VS Code. Point it at an OpenAPI or Swagger spec, an API docs link, a cURL command, a Postman collection, a Grap
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
Eased is a library of motion-first React components for shadcn, installed with the shadcn CLI.
Comments