Ombre Brain
by jian229
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OMBRE_API_KEY | No | LLM API key (any OpenAI-compatible API). Optional — if not set, the server falls back to local keyword extraction for dehydration and auto-tagging. | |
| OMBRE_BASE_URL | No | API endpoint for the OpenAI-compatible API, e.g. https://api.deepseek.com/v1, http://123.1.1.1:7689/v1, or http://your-ollama:11434/v1. | |
| OMBRE_HOOK_URL | No | Server address used by the Claude Code SessionStart hook (default is http://localhost:8000). | |
| OMBRE_HOOK_SKIP | No | Set to 1 to temporarily disable the Claude Code SessionStart hook that auto-calls `breath`. | |
| OMBRE_TRANSPORT | No | Overrides the transport mode: `stdio` for local use or `streamable-http` for remote use. Defaults to `stdio`. | |
| OMBRE_BUCKETS_DIR | No | Overrides the memory bucket storage path. Defaults to `./buckets/` in the project directory. |
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