OpenJarvis 1.0 Release: Local-First Personal AI via Ollama

OpenJarvis 1.0 is an open-source framework for building personal AI agents that run on local hardware, now featuring built-in support for Ollama. Developed by Stanford’s Hazy Research and Scaling Intelligence labs, the project is part of the ‘Intelligence Per Watt’ research initiative focused on efficient local AI.

Local-First Architecture

OpenJarvis shifts the default for personal AI from cloud-dependency to local execution. While local models can handle most daily reasoning and chat tasks, OpenJarvis ensures models run locally by default, making cloud access optional. The framework tracks accuracy alongside energy consumption, latency, and cost.

Integration with Ollama

OpenJarvis integrates directly with Ollama to manage and execute models. Users can pull specific models through the jarvis CLI and assign them to queries or set them as defaults in the configuration file.

Model Configuration

Users can specify a default model and engine in ~/.openjarvis/config.toml using the following configuration:

[intelligence]
default_model = "qwen3.5:35b"
preferred_engine = "ollama"

Built-in Agent Presets

OpenJarvis provides ready-to-run presets that bundle agents with the necessary tools and engines for specific workflows:

Morning Briefing Agent

The morning-digest-mac preset allows users to generate a daily briefing by connecting the agent to their calendar, email, and current news feeds.

Deep Research Agent

The deep-research preset enables research across the web and local documents. It supports indexing local directories via jarvis memory index and provides answers with citations.

Local Coding Agent

The code-assistant preset provides a coding agent capable of writing and executing Python code directly on the user's machine to complete tasks.

Installation and Setup

OpenJarvis is available for macOS, Linux, and Windows (via WSL2 or a desktop app). The installation process involves installing Ollama and running the provided install script:

curl -fsSL https://open-jarvis.github.io/OpenJarvis/install.sh | bash

Sources

Related

  • Project
    open-jarvis/OpenJarvis

    A framework for local-first personal AI agents that allows users to run intelligence on their own devices, reducing reliance on cloud APIs.

  • 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.

  • Dispatch
    Ollama Windows Preview Release

    Ollama has launched a preview version for Windows, enabling users to run, pull, and create large language models locally with native GPU acceleration and API access.

  • Dispatch
    OpenClaw personal AI coding assistant launch by Ollama

    Ollama announced OpenClaw, a locally‑run personal AI assistant that connects WhatsApp, Telegram, Slack, Discord, iMessage and other messaging platforms to AI coding agents via a centralized gateway, enabling private, cross‑platform code assistance.

  • Project
    akshayaggarwal99/jarvis-ai-assistant

    An open-source voice dictation tool that converts speech to text anywhere on your system, supporting local transcription and LLM post-processing for privacy and speed.