Kagura Memory Cloud
Officialby kagura-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JWT_SECRET | Yes | Secret for JWT tokens (auto-generated by setup_env). Required. | |
| QDRANT_URL | No | Qdrant server URL. Defaults to localhost:6333 in docker-compose. | |
| ENVIRONMENT | No | Environment: 'development' or 'production'. Set to 'production' for GCP/cloud deployments. | development |
| CORS_ORIGINS | No | Comma-separated list of allowed CORS origins (e.g., frontend URL). | |
| DATABASE_URL | No | PostgreSQL connection string. Defaults are provided by docker-compose for local development. | |
| API_KEY_SECRET | Yes | Secret for API key encryption (auto-generated by setup_env). Required. | |
| OPENAI_API_KEY | No | OpenAI API key for embeddings. Either this or a self-hosted inference server is required for memory features. | |
| GITHUB_CLIENT_ID | No | GitHub OAuth2 client ID (optional, for GitHub login). | |
| GOOGLE_CLIENT_ID | No | Google OAuth2 client ID (optional, for Google login). | |
| EMBEDDING_PROVIDER | No | Embedding provider: 'openai' (default) or 'self_hosted' for local embeddings via Ollama/vLLM. | openai |
| GITHUB_CLIENT_SECRET | No | GitHub OAuth2 client secret (optional, for GitHub login). | |
| GOOGLE_CLIENT_SECRET | No | Google OAuth2 client secret (optional, for Google login). | |
| SELF_HOSTED_BASE_URL | No | Base URL for the self-hosted embedding server (used when EMBEDDING_PROVIDER=self_hosted). | http://localhost:11434 |
| KAGURA_VECTOR_BACKEND | No | Vector backend: 'qdrant' (default) or 'lance' for embedded LanceDB (single-process, self-hosted). | qdrant |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessResponsive