Cowork
by slashman413
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COWORK_PORT | No | Override the HTTP port without editing any file: `COWORK_CONFIG=~/.cowork/config.staging.json COWORK_PORT=6900 npm start` | 6868 |
| COWORK_CONFIG | No | Path to the config file. "The real config is read from `~/.cowork/config.json` by default. Point at a different file with the `COWORK_CONFIG` env var (and override the port / API key without editing any file)" | ~/.cowork/config.json |
| COWORK_API_KEY | No | Set to require an API key for authentication. "set `COWORK_API_KEY` to require a key"; equivalently set `server.apiKey` in the config (null = open). | |
| COWORK_ARTIFACTS_DIR | No | Directory local brains save output artifacts to; the dispatcher collects the files from disk. Remote brains also save here and upload each file via `POST /api/artifacts/:taskId/:file`. | |
| COWORK_ROSTER_TTL_MS | No | How long the in-memory Agencies catalog is cached before rescanned (default 30000). Set `0` to rescan on every query, or a larger value to reduce disk work. | 30000 |
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
ResponsivenessSyncing