mybrain
by robertsfeir
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BRAIN_SCOPE | No | ltree scope for isolating thoughts (default: personal). | |
| OLLAMA_HOST | No | Ollama host URL (required if provider is ollama). | |
| DATABASE_URL | Yes | PostgreSQL connection URL (must have pgvector and ltree extensions). | |
| OLLAMA_MODEL | No | Ollama model name (default: gte-qwen2-1.5b-instruct). | |
| MYBRAIN_QUIET | No | Suppress shell wrapper output. | |
| EMBEDDING_PROVIDER | No | Embedding provider: ollama (local) or openrouter (cloud). | |
| OPENROUTER_API_KEY | No | OpenRouter API key (required if provider is openrouter). | |
| MYBRAIN_ASYNC_STORAGE | No | Enable async embedding storage (default: false). | |
| MYBRAIN_HEALTH_TIMEOUT | No | Health check timeout in seconds (shell wrapper). |
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
ActivityInactive
ResponsivenessNo issues