

Local-first framework for building on-device personal AI agents with tools, memory, and learning capabilities. Runs entirely on-device with five composable primitives: intelligence, engine, agents, tools & memory, and learning.
OpenJarvis is an open-source framework from Stanford's Scaling Intelligence Lab for personal AI agents that run entirely on-device. Released in March 2026, it provides shared primitives for building on-device agents, efficiency-aware evaluations, and a learning loop that improves models using local trace data.
Stanford's Intelligence Per Watt research showed that local language models already handle 88.7% of single-turn chat and reasoning queries, with intelligence efficiency improving 5.3× from 2023 to 2025. Traditional personal AI design introduces latency, recurring cost, and data exposure concerns, especially for assistants/agents that operate over personal files, messages, and persistent user context.
OpenJarvis is structured around five composable primitives:
OpenJarvis prioritizes efficiency, treating energy, FLOPs, latency, and cost as key constraints alongside task quality. It incorporates a hardware-agnostic telemetry system for profiling energy on NVIDIA GPUs, AMD GPUs, and Apple Silicon.
Developer interfaces include a browser application, a desktop application for macOS, Windows, and Linux, a Python SDK, and a command-line interface (CLI), with all core functionality operating without a network connection.
Open-source and free to use under an open-source license.
Loading more......