open-jarvis/OpenJarvis

Personal AI, On Personal Devices

What it solves

OpenJarvis provides a software stack to make local-first personal AI agents practical. It addresses the dependency on cloud APIs for personal AI, allowing users to run agents on their own devices by default and only calling the cloud when necessary.

How it works

It is a framework built around three core pillars: shared primitives for building on-device agents, evaluations that prioritize energy, FLOPs, latency, and cost alongside accuracy, and a learning loop that uses local trace data to improve models.

Who it’s for

Developers and researchers who want to build personal AI agents that run locally on personal devices, as well as users who want to pre-configured agents for tasks like daily briefings, research, and coding assistance.

Highlights

  • Local-First Architecture: Designed to run on personal devices using tools like Ollama.
  • Diverse Agent Modes: Supports on-demand, scheduled, and continuous execution modes.
  • Citations and Research: Includes a deep_research agent capable of multi-hop research with citations across web and local documents.
  • Extensible Skill System: Uses the agentskills.io open standard to allow agents to discover and install skills from public sources like Hermes Agent and OpenClaw.
  • Built-in Agents: Ships with eight specialized agents, including a morning_digest for spoken briefings and a native_openhands for Python code execution.

Related

  • Dispatch
    OpenJarvis 1.0 Release: Local-First Personal AI via Ollama

    OpenJarvis 1.0 is an open-source framework for building local-first personal AI agents that integrates with Ollama to run models on personal hardware.

  • Project
    openyak/openyak

    A local-first agent runtime and desktop workspace that allows AI agents to interact with local files, native apps, and a managed browser while keeping data on the user's machine.

  • Project
    Rose22/openlumara

    A modular, local-first AI agent framework designed for token efficiency and personal life management, supporting multiple interfaces and sandboxed shell execution.

  • Project
    elizaOS/eliza

    An open-source TypeScript framework and product stack for creating autonomous AI agents with a plugin-based architecture and support for local on-device inference.

  • Project
    zeenie-ai/OpenCompany

    An open-source, self-hosted no-code canvas for building AI agent workflows that connects LLMs to over 30 services and allows for local model execution.