• Home
  • Categories
  • Pricing
  • Submit
    Built with
    Ever Works
    Ever Works

    Connect with us

    Stay Updated

    Get the latest updates and exclusive content delivered to your inbox.

    Product

    • Categories
    • Pricing
    • Help

    Clients

    • Sign In
    • Register
    • Forgot password?

    Company

    • About Us
    • Admin
    • Sitemap

    Resources

    • Blog
    • Submit
    • API Documentation
    All product names, logos, and brands are the property of their respective owners. All company, product, and service names used in this repository, related repositories, and associated websites are for identification purposes only. The use of these names, logos, and brands does not imply endorsement, affiliation, or sponsorship. This directory may include content generated by artificial intelligence.
    Copyright © 2025 Awesome Vector Databases. All rights reserved.·Terms of Service·Privacy Policy·Cookies
    Decorative pattern
    Decorative pattern
    1. Home
    2. Llm Frameworks
    3. OpenJarvis

    OpenJarvis

    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.

    Overview

    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.

    Key Motivation

    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.

    Five Core Primitives

    OpenJarvis is structured around five composable primitives:

    1. Intelligence - The model selection layer that manages the full catalog of local models across providers
    2. Engine - The inference runtime supporting Ollama, vLLM, SGLang, llama.cpp, cloud APIs, and more, which auto-detects your hardware and recommends the best fit
    3. Agents - Multi-step reasoning with tool use, featuring seven built-in agent types from simple chat to orchestrated workflows
    4. Tools & Memory - Web search, calculator, file I/O, code interpreter, retrieval, and any external MCP server
    5. Learning - Your AI gets better over time, with every interaction generating traces that drive automatic improvements to model weights, prompts, and agent behavior

    Key Features

    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.

    Pricing

    Open-source and free to use under an open-source license.

    Surveys

    Loading more......

    Information

    Websiteopen-jarvis.github.io
    PublishedMar 24, 2026

    Categories

    1 Item
    Llm Frameworks

    Tags

    3 Items
    #on-device#local-first#ai-agents

    Similar Products

    6 result(s)

    Letta

    Platform for building stateful AI agents with advanced memory that can learn and self-improve over time. Uses OS-inspired approach with main context as RAM and external storage as disk.

    smolagents

    Minimalist AI agent framework from Hugging Face that enables powerful agents in just a few lines of code with a code-first approach and support for any LLM.

    Dify

    Open-source LLM app development platform with an intuitive interface that combines AI workflow, RAG pipeline, agent capabilities, model management, and observability features for rapid prototyping and production deployment.

    Agentic RAG

    An advanced RAG architecture where an AI agent autonomously decides which questions to ask, which tools to use, when to retrieve information, and how to aggregate results. Represents a major trend in 2026 for more intelligent and adaptive retrieval systems.

    Featured

    LanceDB

    Open-source embedded vector database built on the Lance columnar format, supporting disk-based storage without data movement and offering seamless Python and JavaScript integration for local and edge AI use cases.

    Hamming Distance for Binary Vector Search

    Distance metric for comparing binary vectors using XOR operations, enabling efficient similarity search with dramatically reduced storage requirements compared to full-precision vectors.