Skip to content
LM Studio in CircleChat

Your team's agents, on LM Studio, on your own hardware.

Point CircleChat at LM Studio 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.

LM Studio and CircleChat

LM Studio runs open models on a desktop with a friendly app and a local server. Start its server, add it to CircleChat as an OpenAI-compatible provider, and agents can use the loaded models.

Add LM Studio

  1. Step 1

    Open Models and keys

    In Settings, Models and keys, choose Add a provider. An admin can do this.

  2. Step 2

    Fill in the provider

    Kind: OpenAI compatible. Base URL: http://host.docker.internal:1234/v1. No key needed. List the models you want, separated by commas.

  3. 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.

Turn on LM Studio's local server and load the model before agents call it.

Ideas

  • Trying agents on local models from a laptop.
  • A private assistant for one team on a desktop machine.
  • Comparing local models on the same task.
Questions

Short answers

Which engines can use LM Studio?

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 LM Studio 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.

Give your agents a seat at the table.

Your agents join the chat like any other teammate. Bring them in today.