llm-sidecar
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Local inference endpoint. | http://localhost:11434 |
| SEARXNG_URL | No | Where to find SearXNG. | http://localhost:8888 |
| LLM_SIDECAR_HOST | No | Daemon bind host. | 127.0.0.1 |
| LLM_SIDECAR_PORT | No | Daemon bind port. | 4001 |
| LLM_SIDECAR_NO_UI | No | Set to disable the dashboard UI. | |
| LLM_SIDECAR_TOKEN | No | Require Authorization: Bearer token for API access. | |
| LLM_SIDECAR_BUDGET | No | Budget level: free, cheap, best. | free |
| OPENROUTER_API_KEY | No | API key for OpenRouter. Unset means local-only. | |
| LLM_SIDECAR_NO_CACHE | No | Set to disable caching. | |
| LLM_SIDECAR_NO_LEDGER | No | Set to disable the usage ledger. | |
| LLM_SIDECAR_MODEL_FAST | No | Lock the fast tier to a specific model. | |
| LLM_SIDECAR_MODEL_BALANCED | No | Lock the balanced tier to a specific model. | |
| LLM_SIDECAR_MODEL_POWERFUL | No | Lock the powerful tier to a specific model. | |
| LLM_SIDECAR_SEARCH_PROVIDER | No | Search provider: auto, ddg, searxng. | auto |
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