OpenCode Brain
by Adityaladi
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GRAPH_PATH | No | Knowledge graph persistence path | ~/.opencode-brain/graph.json |
| QDRANT_HOST | No | Qdrant server host | localhost |
| QDRANT_PORT | No | Qdrant server port | 6333 |
| FAST_MODEL_ID | No | Fast default LLM for note construction and extraction | Qwen/Qwen3-4B-Instruct-2507 |
| HARD_MODEL_ID | No | Hard fallback model for synthesis and memory evolution | Qwen/Qwen3-30B-A3B-Instruct-2507 |
| OBSIDIAN_HOST | No | Obsidian REST API URL | http://localhost:27123 |
| EMBEDDING_MODEL | No | Embedding model | sentence-transformers/all-MiniLM-L6-v2 |
| OBSIDIAN_API_KEY | No | Obsidian Local REST API key (empty disables sync) | |
| QDRANT_COLLECTION | No | Collection name | opencode_brain |
| FAST_MODEL_PROVIDER | No | Inference provider for the fast model (overridden to nscale in .env) | featherless-ai |
| HARD_MODEL_PROVIDER | No | Inference provider for the hard model | featherless-ai |
| HUGGINGFACE_API_KEY | Yes | Required | |
| STALE_DAYS_THRESHOLD | No | Days before a note is stale | 45 |
| STALE_ACCESS_THRESHOLD | No | Min accesses to be immune from archival | 2 |
| OBSIDIAN_VAULT_SUBFOLDER | No | Subfolder in vault for notes | brain |
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
ActivitySlowing
ResponsivenessNo issues