OAH Agent Gateway
by Ruthwik10
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OAH_SOURCE | No | live (sandbox), snapshot (bundled copy) or auto (live, fall back to snapshot) | auto |
| NVIDIA_MODEL | No | Model for the console agent (NVIDIA API; reasoning disabled for fast demos) | nvidia/nemotron-3-super-120b-a12b |
| OAH_FHIR_BASE | No | FHIR server implementing the OAH IG to read from (and write to, if enabled) | https://sandbox.hl7europe.eu/oneaquahealth/fhir |
| NVIDIA_API_KEY | No | From build.nvidia.com; enables the chat agent in the web console | |
| NVIDIA_BASE_URL | No | NVIDIA OpenAI-compatible endpoint | https://integrate.api.nvidia.com/v1 |
| OAH_AGENT_MODEL | No | Anthropic model for the console agent | claude-sonnet-5-5 |
| OAH_ALLOW_WRITE | No | Set to 1 to allow approved drafts to be POSTed to the sandbox | off |
| ANTHROPIC_API_KEY | No | Fallback provider for the chat agent, used when NVIDIA_API_KEY is not set |
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