OpenClaw personal AI coding assistant launch by Ollama

TL;DR

OpenClaw is a new personal AI assistant from Ollama that bridges popular messaging apps to AI coding agents while running locally on the user’s device, preserving privacy and supporting large‑context models.

What OpenClaw Is

OpenClaw is a self‑hosted gateway that lets you chat with AI coding agents from any of your favorite messaging platforms—WhatsApp, Telegram, Slack, Discord, iMessage, and more. Because the service runs on your own hardware, all conversation history and generated code stay on your device and are never sent to external servers.

Quick Installation

  • Unix/macOS: curl -fsSL https://openclaw.ai/install.sh | bash
  • Windows: iwr -useb https://openclaw.ai/install.ps1 | iex

These commands install the OpenClaw daemon and its dependencies in a single step.

Running OpenClaw with Ollama

After installation, launch the gateway directly with an Ollama model:

ollama launch openclaw

To edit configuration without starting the service, add the --config flag:

ollama launch openclaw --config

The gateway automatically reloads when a configuration change is detected, so you can iterate on settings without manual restarts.

Recommended Model Characteristics

OpenClaw’s coding tasks benefit from a large context window. Ollama recommends models with at least 64 k token context length. The following models are known to work well:

Model Strength
qwen3-coder Optimized for coding tasks
glm-4.7 Strong general‑purpose performance
glm-4.7-flash Balanced speed and capability
gpt-oss:20b Balanced performance and speed
gpt-oss:120b Higher capability for complex code

Cloud Model Options

Ollama also offers free‑tier cloud models that can be used with OpenClaw:

Model Strength
kimi-k2.5 1 T‑parameter model excelling at agentic tasks
minimax-m2.1 Excellent multilingual support
glm-4.7 Strong general‑purpose model
gpt-oss:20b Balanced performance and speed
gpt-oss:120b Improved capability

All models are searchable on ollama.com.

User Interface Snapshots

  • Configuration screen – shows the Ollama launch UI where you select a model and adjust settings.
  • WhatsApp connection – demonstrates a live chat with the assistant inside a WhatsApp conversation.

OpenClaw configuration screen

OpenClaw in WhatsApp

Naming History

OpenClaw was previously released under the names Clawdbot and Moltbot. The legacy command clawdbot remains functional as an alias for backward compatibility.

Implications

  • Privacy‑first workflow: By running entirely on user hardware, OpenClaw eliminates the need to trust third‑party APIs with proprietary code.
  • Cross‑platform accessibility: Developers can invoke AI assistance from any messaging app they already use, reducing context switching.
  • Scalable reasoning: Support for 64 k token contexts enables the assistant to handle large codebases or multi‑file refactoring tasks in a single prompt.

These features position OpenClaw as a practical bridge between everyday communication tools and advanced AI coding agents, potentially accelerating developer productivity while maintaining data sovereignty.

Sources

Related

  • Dispatch
    Ollama 0.17: Simplified Setup for OpenClaw AI Assistant

    Ollama 0.17 introduces a single-command installation process for OpenClaw, a personal AI assistant capable of managing emails, calendars, and messaging apps on local hardware.

  • Project
    openclaw/openclaw

    OpenClaw is a self-hosted personal AI assistant that connects AI models and tools to your favorite messaging channels and local devices.

  • Dispatch
    Ollama and Continue: Setting Up an Open-Source AI Code Assistant

    Ollama and Continue enable developers to build a fully open-source, local AI coding assistant within VS Code and JetBrains using models like Codestral, Llama 3, and DeepSeek Coder.

  • Project
    ollama/ollama

    Ollama is a cross‑platform runtime that lets you download and run open‑source large language models locally. It offers a CLI, a REST API (localhost:11434), and official Python/JS SDKs, plus many community integrations (web UIs, LangChain, AutoGPT, etc.). Install with a one‑line script or Docker, then launch models like `ollama run gemma4` or use `ollama launch` to connect to coding assistants or personal bots.

  • Dispatch
    Ollama OpenAI Compatibility Update

    Ollama has introduced built-in compatibility with the OpenAI Chat Completions API, allowing users to run local models using existing OpenAI-compatible tools and libraries.