openclaw

OpenClaw is an open-source personal AI agent that runs on your own devices and bridges chat apps (WhatsApp, Telegram, Slack, Discord, iMessage, and more) to a model through a local gateway. It speaks any OpenAI-compatible endpoint, so it can run entirely against local Bonsai — no data leaves your machine.

Step 1: Serve Bonsai

./scripts/start_llama_server.sh
# Base URL: http://localhost:8080/v1

./scripts/start_mlx_server.sh
# Base URL: http://localhost:8081/v1

Agent work leans hard on tool calling and multi-step instructions; prefer Ternary 27B, which is trained for native tool calling.

Install OpenClaw

curl -fsSL https://openclaw.ai/install.sh | bash

This detects your OS, installs Node if needed, installs OpenClaw, and launches onboarding. See the install docs for Windows, Docker, and other options.

Run the setup wizard

 openclaw config

Under Model/auth provider choose Custom Provider and enter:

Prompt	Value
API base URL	`http://localhost:8080/v1` (or your endpoint from step 1)
API key	any non-empty string, e.g. `not-needed`
Endpoint compatibility	OpenAI-compatible
Model ID	`Ternary-Bonsai-27B-Q2_0.gguf` or `Ternary-Bonsai-27B-mlx-2bit` (or check with `curl http://localhost:8081/v1/models`)
Display name	e.g. `ternary-bonsai-27B`

Launch

openclaw dashboard

Give it a task. Requests appear in your Bonsai server log, confirming the agent is running fully locally.

⌘I

Get started

Models

Download

Run Locally

Integrations

Resources

Getting Started

Step 1: Serve Bonsai

​Step 1: Serve Bonsai

Step 1: Serve Bonsai