Stanford Researchers Release OpenJarvis | Garry Tan Releases gstack

Here is your today’s AI Dev Brief from Marktechpost, covering core research, models, infrastructure tools, and applied updates for AI developers and researchers.

Stanford researchers released OpenJarvis, an open framework for building personal AI agents that run entirely on-device, with a local-first design that makes cloud usage optional. The system is structured around five primitives—Intelligence, Engine, Agents, Tools & Memory, and Learning—to separate model selection, inference, orchestration, retrieval, and adaptation into modular components. OpenJarvis supports backends such as Ollama, vLLM, SGLang, llama.cpp, and cloud APIs, while also providing local retrieval, MCP-based tool use, semantic indexing, and trace-driven optimization. A key part of the framework is its focus on efficiency-aware evaluation, tracking metrics such as energy, latency, FLOPs, and dollar cost alongside task performance.… Read the full analysis/article here.

Garry Tan’s gstack is an open-source repository that adds 8 opinionated workflow skills to Claude Code for product planning, engineering review, code review, shipping, browser automation, QA, cookie setup, and retrospectives. Its main technical feature is a persistent headless Chromium daemon that keeps browser state, cookies, tabs, and login sessions alive across commands, making browser-driven debugging and testing faster and more practical. Built with Bun, Playwright, and a local localhost-based daemon model, gstack is designed to connect code changes with actual application behavior through route-aware QA and structured release workflows.… Read the full analysis/article here.

▶ How to Build an Autonomous Machine Learning Research Loop in Google Colab Using Andrej Karpathy’s AutoResearch Framework for Hyperparameter Discovery and Experiment Tracking Codes Tutorial

▶ How to Design a Streaming Decision Agent with Partial Reasoning, Online Replanning, and Reactive Mid-Execution Adaptation in Dynamic Environments Codes Tutorial

▶ How to Build a Self-Designing Meta-Agent That Automatically Constructs, Instantiates, and Refines Task-Specific AI Agents Codes Tutorial

▶ How to Build a Risk-Aware AI Agent with Internal Critic, Self-Consistency Reasoning, and Uncertainty Estimation for Reliable Decision-Making Codes Tutorial

150+ more open codes/notebooks here ➡️