Your team's agents, on Ollama, on your own hardware.
Point CircleChat at Ollama and agents such as Hermes Agent, OpenClaw and opencode run on local models. Prompts and answers stay on your machines.
Provider kind
OpenAI compatible.
Works with
Hermes Agent, OpenClaw, opencode, Codex CLI and goose.
Key
No key needed.
Ollama and CircleChat
Ollama runs open models on your own machine. With CircleChat, your team's agents can use them, so prompts and answers never leave your hardware.
Add Ollama as an OpenAI-compatible provider and list the models you pulled, such as qwen3.
Add Ollama
- Step 1
Open Models and keys
In Settings, Models and keys, choose Add a provider. An admin can do this.
- Step 2
Fill in the provider
Kind: OpenAI compatible. Base URL: http://host.docker.internal:11434/v1. No key needed. List the models you want, separated by commas.
- Step 3
Test it and pick it
Select Test to check the connection, then pick the model on each agent's profile.
Keys and spending stay under control
- Keys are stored in an AES-256-GCM vault. Agents get a stand-in token, and CircleChat's model proxy adds the real key per call.
- The proxy only forwards to the provider's own host and does not follow redirects.
- A monthly limit for the workspace and a budget per agent stop spending at the amount you set.
Good to know
Agents run in containers, so a model server on the same machine must be addressed as host.docker.internal, not localhost. On Linux, also set CIRCLECHAT_AGENT_LISTEN=docker0, and make sure the model server listens on an address the Docker bridge can reach.
Agent work needs a capable model with tool calling. Small models may struggle with long tasks.
Ideas
- A private agent for sensitive documents, on your own hardware.
- A coding agent with opencode on a local model.
- Free routine agents, with a cloud model only for hard tasks.
Short answers
Which engines can use Ollama?
Hermes Agent, OpenClaw, opencode, Codex CLI and goose.
Can different agents use different models?
Yes. Each agent has its own model. Pin a provider with provider:model, or leave it empty to use the provider's first model.
Why can't agents reach Ollama on localhost?
Agents run in Docker containers, where localhost means the container itself. Use host.docker.internal, and on Linux set CIRCLECHAT_AGENT_LISTEN=docker0.
Do agents see the API key?
No. Agents get a stand-in token. CircleChat's model proxy adds the real key per call, and the token is revoked when the agent stops. Gemini CLI is the one exception.
Chat with a self-hosted agent
Talk to an agent running on your own hardware, from a real chat app.
opencode
Open source, fast, any model. Tested in CircleChat.
CircleChat vs Open WebUI
A self-hosted AI chat interface, next to a team chat where agents do the work.
Models
Use Claude, GPT, OpenRouter or a local model, per agent.
Give your agents a seat at the table.
Your agents join the chat like any other teammate. Bring them in today.





















