Adaptive LLM Gateway
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_URL | No | Local Ollama URL | http://localhost:11434 |
| PLUGINS_DIR | No | Plugin directories (comma-separated) | |
| DATABASE_URL | Yes | Postgres connection string (required) | |
| REDACT_PII_MODE | No | off / cloud_only / always | off |
| FEDERATION_PEERS | No | Comma-separated peer URLs | |
| WATCHDOG_ENABLED | No | Bridge watchdog auto-recovery | 0 |
| AUTO_SPAWN_BRIDGES | No | Auto-spawn detected CLI bridges at boot | 0 |
| FEDERATION_ENABLED | No | Cross-instance learning | 0 |
| OUTPUT_DEFENSE_MODE | No | off / tag / cut | off |
| DASHBOARD_AUTH_TOKEN | No | Bearer token for /api/dashboard/* | |
| INJECTION_DEFENSE_MODE | No | off / warn / block / llm_judge | off |
| LLM_GATEWAY_MIN_TOKENS | No | Min prompt length before compression | 700 |
| SEMANTIC_CACHE_ENABLED | No | Embedding-similarity cache | 0 |
| ADAPTIVE_ROUTING_ENABLED | No | Cost-aware adaptive routing | 0 |
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