OL
toolOllama
Downloads, manages, and serves a broad catalog of local language and vision models through a simple API.
What it provides
Connect an HTTPS inference API. Model weights stay on CPU/GPU infrastructure and are never installed inside the 4 GB bot.
Connection requirements
An HTTPS-reverse-proxied Ollama server
- Protocol
- OpenAI-compatible REST
- Endpoint
https://ollama.example.com- Authentication
- Choose the mode required by your service
Where to add it
Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.