ToolsThe story, in brief

Meet OpenJarvis: A Local-First Framework for On-Device Personal AI Agents with Tools, Memory, and Learning

800× lower API costs. Stanford just open-sourced OpenJarvis, a local-first framework that runs agents, memory, and learning entirely on-device—within 3.2 points of cloud models.

Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

Open-source on-device AI agents represent a fundamental shift in deployment economics. This framework challenges the cloud-dependent model that has defined the current AI economy, offering builders a path to drastically reduce inference costs while maintaining near-parity performance.

The key facts

7 to know
  1. OpenJarvis is an open-source framework for on-device AI agents

  2. Runs inference, agents, memory, and learning entirely locally

  3. Decomposes personal AI into five composable primitives: Intelligence, Engine, Agents, Tools & Memory, Learning

  4. Achieves within 3.2 points of best cloud models

  5. 800× lower marginal API cost vs. cloud alternatives

  6. Released by Stanford researchers

  7. Available open-source

Go to the source

MarkTechPostmarktechpost.com

Publisher excerpt: Stanford researchers released OpenJarvis, an open-source framework that runs inference, agents, memory, and learning entirely on-device. It decomposes a personal AI system into five composable primitives — Intelligence, Engine, Agents, Tools & Memory, and Learning — and lands within 3.2 points of…
Read original report
Back to today's editionMore tools news

The wider picture

View all
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools01

OpenAI nabs key Patreon execs ahead of upcoming announcement

OpenAI is building a creator-focused product suite with deep domain expertise (Patreon's co-founder + product + engineering leads). This signals a major new revenue and engagement vector for ChatGPT — and a direct threat to Patreon's existing creator economy.

The Verge AI
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Tools02

Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model

A practical, deployment-ready layer for a common production pattern — classification over generation — that practitioners can drop into existing LLM stacks immediately. No fine-tuning required.

MarkTechPost
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools03

SpeakON Ships a MagSafe AI Voice Button With Its Own Microphone

A hardware-first approach to voice AI workflow — MagSafe button with onboard mic addresses the real friction in voice-to-text-to-action. Relevant to practitioners building voice UX and to the broader consumer AI tooling wave.

MarkTechPost