Ombre-Brain
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OMBRE_API_KEY | No | LLM API key for API-powered dehydration and auto-tagging. Optional; if omitted, falls back to local keyword extraction. | |
| OMBRE_BASE_URL | No | OpenAI-compatible API endpoint for dehydration/tagging, e.g. https://api.deepseek.com/v1. Optional. | |
| OMBRE_HOOK_URL | No | Server URL used by the Claude Code SessionStart hook. Optional. | http://localhost:8000 |
| OMBRE_HOOK_SKIP | No | Set to 1 to temporarily disable the Claude Code SessionStart auto-breath hook. Optional. | |
| OMBRE_TRANSPORT | No | Transport mode. Use 'stdio' for local or 'streamable-http' for remote/HTTP access. | stdio |
| OMBRE_BUCKETS_DIR | No | Overrides the bucket storage path. Defaults to ./buckets/ if not set. |
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
ActivityNo data
ResponsivenessSyncing