OpenJarvis 1.0 发布，内置 Ollama 支持本地个人 AI 智能体
OpenJarvis: a local-first personal AI is now available to run with Ollama · Ollama Blog
斯坦福 Hazy Research 与 Scaling Intelligence 实验室开源框架 OpenJarvis 发布 1.0 版本，内置对 Ollama 的支持，用于在本地硬件上构建个人 AI 智能体。该框架将本地运行设为默认、云端可选，并同时追踪能耗、成本、延迟与准确率。它自带晨间简报、跨文件研究、本地编码等可直接运行的智能体预设，macOS 和 Linux 可通过安装脚本自动检测已有的 Ollama 安装，Windows 需在 WSL2 中运行或安装桌面应用。
正文
当前显示原文，中文全文译文尚未就绪。
May 28, 2026
OpenJarvis is an open-source framework for building personal AI agents that run on your own hardware. It’s built by Stanford’s Hazy Research and Scaling Intelligence labs, as part of their “Intelligence Per Watt” research into efficient local AI.
Local models can already handle most day-to-day chat and reasoning, yet most personal AI still sends every request to the cloud. OpenJarvis makes local-first the default. Models run locally, and the cloud is optional. Energy, cost, and latency are tracked alongside accuracy.
Version 1.0 is now available with built-in support for Ollama.
Install Ollama
Download Ollama for macOS, Windows, or Linux.
Install OpenJarvis
On macOS or Linux, the install script sets up everything you need and auto-detects your existing Ollama installation:
On Windows, run that command inside WSL2, or install the desktop app.
Then run jarvis to start.
Choosing models
The install script sets up a starter model so you can begin right away, but you can choose your own. Pull any model through Ollama and use it for a query:
To set a default model, add it to ~/.openjarvis/config.toml:
Built-in agents
OpenJarvis ships with ready-to-run presets. Each one bundles an agent with the engines and tools it needs to run.
Morning briefing
Generate a morning briefing agent using your calendar, email, and the day’s news:
Research across files
Ask a question to perform research across the web and your local documents, returning an answer with citations:
Local coding agent
A code agent that writes and runs Python on your machine to get tasks done:
OpenJarvis on GitHub; OpenJarvis documentation; v1.0.0 release notes