serena Docker & Self-Hosted Deployment

GitHub

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

30,617 stars Python Python 1 file · ~107,518 tokens #agent#ai#ai-coding#claude#claude-code#codex#ide#jetbrains
RAW Compose
1. Pull Image (DOCKERHUB) docker pull library/serena
2. Docker Run (1-Click Launch) docker run -d --name serena -p 9121:9121 --restart always serena:latest
3. Podman Run podman run -d --name serena -p 9121:9121 --restart always serena:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/library/serena:latest
5. ORAS Pull (OCI Artifact) oras pull serena:latest
6. Compose Deployment docker compose up -d
compose.yaml
Download .yml 
services:
  serena:
    image: serena:latest
    # To work with projects, you must mount them into /workspace/ in the container:
    # volumes:
      # - ./my-project:/workspace/my-project
      # - /path/to/another/project:/workspace/another-project
    build:
      context: ./
      dockerfile: Dockerfile
      target: production
    ports:
      - "127.0.0.1:${SERENA_PORT:-9121}:9121"
      - "127.0.0.1:${SERENA_DASHBOARD_PORT:-24282}:24282"
    environment:
      - SERENA_DOCKER=1
    command:
      - "uv run --directory . serena-mcp-server --transport sse --port 9121 --host 0.0.0.0"
      # Alternatively add further arguments, e.g. a context
      # - "uv run --directory . serena-mcp-server --transport sse --port 9121 --host 0.0.0.0 --context ide"