brain-engine
by LiorHalfon
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORY_HOST | No | Bind address. Keep it on localhost, since the service has no authentication. | 127.0.0.1 |
| MEMORY_PORT | No | Service port. | port from brain.toml |
| MEMORY_ROOT | No | The Markdown folder. It moves only the Markdown; the state stays in the vault. | <vault>/<memory_dir> |
| MEMORY_ACTOR | No | Written to each new memory's generated.by. | <name>/local |
| MEMORY_VAULT | No | The vault folder, when --vault isn't given. | current directory |
| MEMORY_ACCESS | No | Access mode. read-only serves only search_memory and get_memory. | read-write |
| OPENAI_API_KEY | No | Graphiti's LLM and embedding calls. Without it the service logs a warning and serves Markdown and FTS. | unset |
| MEMORY_HUMAN_ID | No | Written to verified.by as human:<id> when a memory is verified. | owner |
| MEMORY_GRAPH_MODEL | No | Graphiti's model. | graph_model from brain.toml |
| MEMORY_GRAPH_ENABLED | No | Set to false to serve Markdown and FTS only. | true |
| MEMORY_GRAPH_SMALL_MODEL | No | Graphiti's small model. | graph_small_model from brain.toml |
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
ActivityMaintained
ResponsivenessNo issues