OpenJarvis: a local-first personal AI is now available to run with Ollama

2026-05-27 · Source: Ollama Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Software Development & Engineering · Depth: Novice, quick

Summary

OpenJarvis, an open-source framework developed by Stanford's Hazy Research and Scaling Intelligence labs, enables building personal AI agents that run locally on user hardware. Released on May 28, 2026, with version 1.0, it integrates built-in support for Ollama, making local-first AI the default rather than cloud-dependent solutions. This initiative stems from their "Intelligence Per Watt" research, focusing on efficient local AI. OpenJarvis tracks energy, cost, latency, and accuracy, offering a transparent approach to personal AI. Users can install it via a curl script on macOS/Linux or through WSL2/desktop app on Windows. It supports pulling any Ollama model and includes ready-to-run presets like a morning briefing agent, a deep research agent for local documents and web, and a local coding assistant.

Key takeaway

For AI Engineers developing personal AI applications, OpenJarvis offers a compelling local-first alternative to cloud-dependent solutions. If you prioritize data privacy, cost control, and reduced latency, integrating OpenJarvis with Ollama allows you to deploy agents directly on user hardware. You should explore its built-in presets for tasks like morning briefings or coding assistance to quickly prototype and deploy efficient, user-controlled AI experiences.

Key insights

OpenJarvis provides a local-first, open-source framework for personal AI agents, prioritizing efficiency and user control over cloud reliance.

Principles

• Local-first AI enhances privacy and efficiency.
• Track energy, cost, latency, and accuracy.
• Open-source frameworks enable custom agent development.

Method

Install OpenJarvis via a curl script or desktop app, then pull Ollama models. Configure a default model in config.toml and initialize agents using jarvis init --preset.

In practice

• Use jarvis init --preset morning-digest-mac for briefings.
• Index local documents with jarvis memory index ./docs/.
• Deploy a Python coding agent via jarvis init --preset code-assistant.

Topics

• Local AI
• Personal AI Agents
• Ollama
• Open-source Frameworks
• AI Efficiency
• Hazy Research

Code references

• open-jarvis/OpenJarvis

Best for: AI Architect, NLP Engineer, AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• OpenJarvis: Local-first AI agents that run entirely on-device — OpenJarvis enables local-first AI agents via a modular architecture, reducing cloud dependency and improving efficiency.
• Running AI Models Locally with Ollama Completely Changed My AI Journey — Ollama simplifies running advanced AI models locally, enhancing privacy, speed, and experimentation without cloud dependency.
• Do people actually want local open-source 3D AI generator tools (Modly), or is cloud just better right now ? — Local-first 3D AI generation offers control and privacy but faces hardware and complexity challenges.
• Build Your Own “Private Copilot” in 10 Minutes: Ollama, Continue, and DeepSeek-V3 — Developers can build a private, offline AI coding assistant using local inference engines and optimized models.
• Top AI GitHub Repositories in 2026 — The open-source AI ecosystem is rapidly maturing, driven by local AI, agentic capabilities, and powerful open models.
• I built a local-first autonomous coding agent with a cyberpunk soul — Eve Agent V2 Unleashed (open source) — Eve Agent V2 is an open-source, local-first autonomous coding agent that uses a multi-round agentic loop and diverse tools for complex software development tasks.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Ollama Blog.