Local Grunt Adapter
by OneWave-AI
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOCAL_GRUNT_FAST | No | Model used for routine tasks. | granite4.2:3b |
| LOCAL_GRUNT_HOST | No | Loopback HTTP address for the local model runtime; loopback HTTP only. | http://127.0.0.1:11434 |
| LOCAL_GRUNT_PANEL | No | Set to 0 for headless operation. | 1 on macOS |
| LOCAL_GRUNT_ROOTS | No | Narrow folder or colon-separated list of folders for sample/working files. | Working directory |
| LOCAL_GRUNT_STATE | No | Private state folder for cache, artifacts, and usage metadata. | .state beside the adapter |
| LOCAL_GRUNT_QUALITY | No | Model used for classification, code, and review tasks. | qwen3.5:9b |
| LOCAL_GRUNT_RESERVE_GIB | No | Override the default memory reserve. |
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