OpenJarvis

Stanford Hazy Research's local-first personal AI **harness**: on-device model inference (Ollama built in), agent execution, memory, and learning as shared primitives, with on-demand, scheduled, and continuous agents and evaluations that count energy, latency, and dollars alongside accuracy; a cloud model can tune the local configuration once so run time stays on your own hardware.

memorylocalpython

Stars: 12.9k
Adoption surface: slightly complex
Autonomy: headless
Recovery: none
License: ✅ open-source
Category: Personal agent runtimes

Repository ↗ Example: YC Paper Club talk (37:20) ↗

Related in Personal agent runtimes

OpenClaw
Hermes
AnythingLLM
nanobot
CowAgent
Khoj

Maintain OpenJarvis? Add the badge

Paste this into your README so readers can find the list and see how OpenJarvis compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)