Agents
OpenJarvis: Local AI Framework Now Available
Ollama Bloghigh confidence
Why it matters
- →OpenJarvis enables personal AI to run locally, reducing cloud dependency.
- →It offers potential savings in energy, cost, and latency for AI applications.
- →The framework supports diverse tasks, enhancing personal AI utility.
Stanford's Hazy Research and Scaling Intelligence labs have released OpenJarvis, an open-source framework for building personal AI agents that run locally on your hardware. This local-first approach aims to reduce reliance on cloud services, enhancing energy efficiency and reducing costs and latency. Version 1.0 of OpenJarvis is now available and integrates seamlessly with Ollama, supporting macOS, Windows, and Linux. The framework includes built-in agents for various tasks, such as generating morning briefings and running Python code locally. OpenJarvis represents a significant step towards more efficient and accessible personal AI systems.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1OpenClaw: Personal AI Assistant for Coding
Ollama Blog · February 1, 2026 · Background
- 2DeepSeek launches new open-source AI model V4
MIT Technology Review AI · April 24, 2026 · Background
- 3OpenAI Launches GPT-5.5 as Advanced AI Model
AI News · April 29, 2026 · Background
- 4NVIDIA Enhances OpenClaw for Autonomous AI Agents
NVIDIA Blog · April 30, 2026 · Background
- 5OpenSwarm AI Launches Open-Source Multi-Agent System
Lev Selector · May 8, 2026 · Background
- 6Osaurus Brings Local and Cloud AI Models to Macs
TechCrunch AI · May 15, 2026 · Related
- 7Hugging Face Launches Open Agent Leaderboard
Hugging Face Blog · May 18, 2026 · Background
- 8AI Agents Revolutionize Coding with Claude Code
WIRED AI · May 26, 2026 · Background
What happened next
- 9Local Models Triage OpenClaw Repo for Free
Hugging Face Blog · June 22, 2026 · Related
- 10Microsoft's Orchard Framework Boosts Agentic AI Research
Microsoft Research · August 3, 2026 · Related
- 11OpenAI buys Macs for private AI agents
Wes Roth · September 1, 2026 · Related
- 12OpenAI Launches Agents API for Cloud Agents
OpenAI · September 10, 2026 · Background
- 13Together AI: Fine-tune Jev-like classifier for $17
Together AI Blog · September 23, 2026 · Background
More in Agents
© The AI Daily BriefAgentscoding
Spawn ships 77k code changes monthly with AI agents
Ten-person team at Spawn utilizes an always-on fleet of AI agents to achieve massive monthly code output.
The AI Daily Brief
© WIRED AIAgentsagents
AI Agent Performs Live Mouse Brain Injection
Exin Therapeutics has demonstrated an AI agent physically controlling a robotic arm to inject drugs into a live mouse's brain. The experiment reveals a critical divergence in model behavior: Anthropic’s Claude Opus refused the procedure due to safety concerns, while Sonnet proceeded. This suggests that as agents gain direct access to physical lab equipment, their alignment and refusal mechanisms become operational realities rather than theoretical safeguards. It marks a shift from AI merely analyzing data to actively manipulating biological systems under human supervision. The team initially tested Claude Opus 5.5, but it halted the injection, citing potential harm. Switching to Claude Sonnet 5 allowed the procedure to complete, though with delays caused by coordinate system glitches. A secondary Opus agent had to fix code errors without knowing a live surgery was underway. Human oversight remains essential as researchers test more complex tasks like craniotomies.
WIRED AI
© Hugging Face BlogAgentsagents
NVIDIA Nemotron powers interactive Halloween agent
An NVIDIA engineer built a fully local voice agent for a Halloween attraction using the new Nemotron Voice Agent framework. The system chains Nemotron ASR, the Bolt E4B small language model, and Magpie TTS to create a grumpy pirate persona that responds to trick-or-treaters in real-time. Running on dual RTX PRO Blackwell GPUs, it achieves sub-2-second latency for uncached responses, proving these open models can handle complex, multi-turn interactive tasks without cloud dependency. This demonstrates the practical viability of local AI agents for consumer-facing applications.
Hugging Face Blog