Ombre Brain
by dwwwpfquct
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OMBRE_API_KEY | No | LLM API key for dehydration/compression and auto-tagging (any OpenAI-compatible API). Optional — if not set, the server falls back to local keyword extraction. | |
| OMBRE_BASE_URL | No | API endpoint for any OpenAI-compatible API, e.g. https://api.deepseek.com/v1, http://your-ollama:11434/v1. Default: https://api.deepseek.com/v1 | |
| OMBRE_HOOK_URL | No | Server address used by the Claude Code SessionStart hook. Default: http://localhost:8000 | |
| OMBRE_HOOK_SKIP | No | Set to 1 to temporarily disable the SessionStart hook. | |
| OMBRE_TRANSPORT | No | Override the transport mode: 'stdio' (local) or 'streamable-http' (remote). Default: stdio | |
| OMBRE_BUCKETS_DIR | No | Override the bucket storage path. Default: ./buckets/ (or as set by config.yaml buckets_dir) |
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
ResponsivenessNo issues