Skip to main content
Glama
docker-compose.yaml2.32 kB
version: "3.9" services: ollama: image: ollama/ollama:latest restart: always ollamasetup: image: ollama/ollama:latest depends_on: - ollama restart: "no" environment: - OLLAMA_HOST=ollama:11434 entrypoint: [ "bash", "-c", "ollama pull qwen3:1.7b && ollama pull granite-embedding:278m"] kodit: image: registry.helix.ml/helix/kodit:latest # Replace with a version ports: - "8080:8080" # You may wish to pick a less common port # Start the Kodit MCP server and bind to all interfaces command: ["serve", "--host", "0.0.0.0", "--port", "8080"] restart: unless-stopped depends_on: - vectorchord # Wait for VectorChord to start before Kodit # Configure Kodit environment: # Configure data storage DATA_DIR: /data DB_URL: postgresql+asyncpg://postgres:mysecretpassword@vectorchord:5432/kodit DEFAULT_SEARCH_PROVIDER: vectorchord # External enrichment provider ## This is an Ollama example, please replace with your own ENRICHMENT_ENDPOINT_BASE_URL: http://ollama:11434 ENRICHMENT_ENDPOINT_MODEL: ollama/qwen3:1.7b ENRICHMENT_ENDPOINT_NUM_PARALLEL_TASKS: 3 ENRICHMENT_ENDPOINT_TIMEOUT: 300 ENRICHMENT_ENDPOINT_EXTRA_PARAMS: "{\"extra_body\": {\"think\": false, \"options\": {\"num_predict\": 200, \"temperature\": 0.7}}}" # External embedding provider ## This is an OpenAI example, please replace with your own EMBEDDING_ENDPOINT_API_KEY: sk-proj-xxxx EMBEDDING_ENDPOINT_MODEL: openai/text-embedding-3-small # Sync configuration SYNC_PERIODIC_ENABLED: true SYNC_PERIODIC_INTERVAL_SECONDS: 1800 # 30 minutes SYNC_PERIODIC_RETRY_ATTEMPTS: 3 # Logging configuration LOG_LEVEL: INFO # Set to DEBUG for more detailed logging LOG_FORMAT: json # API Key Configuration API_KEYS: ${KODIT_API_KEYS:-} volumes: - ${KODIT_DATA:-kodit-data}:/data vectorchord: image: tensorchord/vchord-suite:pg17-20250601 environment: - POSTGRES_DB=kodit - POSTGRES_PASSWORD=mysecretpassword volumes: - ${VECTORCHORD_DATA:-kodit-vectorchord}:/var/lib/postgresql/data ports: - "5432" restart: unless-stopped volumes: kodit-data: kodit-vectorchord:

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/helixml/kodit'

If you have feedback or need assistance with the MCP directory API, please join our Discord server