https://scouthub.dev/en/news/The most important global AI news each day, summed up in plain language with a link to the source, plus the newest open-source AI repositories.enTue, 10 Nov 2026 06:00:00 GMT https://github.com/ruvnet/RuViewhttps://scouthub.dev/en/news/2026-11-10/#r36Tue, 10 Nov 2026 06:00:00 GMTRuView turns standard WiFi signals into a spatial intelligence system that tracks presence, movement, and vital signs like breathing and heart rate without cameras. It operates through walls using low-cost ESP32 hardware and integrates natively with smart home platforms like Home Assistant and Apple Home.Tools https://github.com/vercel-labs/json-renderhttps://scouthub.dev/en/news/2026-11-10/#r37Tue, 10 Nov 2026 06:00:00 GMTjson-render is a generative UI framework that enables AI to build dynamic interfaces constrained to a predefined catalog of components and actions. It helps developers reliably stream and render predictable user interfaces across multiple web, mobile, and desktop environments.Design & images https://github.com/opensandbox-group/OpenSandboxhttps://scouthub.dev/en/news/2026-11-10/#r34Tue, 10 Nov 2026 06:00:00 GMTOpenSandbox provides secure, isolated environments to run AI agents, execute code, and manage files directly on your own infrastructure. It scales from local Docker setups to Kubernetes clusters, offering fast runtimes, network access controls, and MCP support.Agents https://github.com/Leonxlnx/earshothttps://scouthub.dev/en/news/2026-11-10/#r38Tue, 10 Nov 2026 06:00:00 GMTearshot gives AI coding agents the ability to hear, analyze, and synthesize sound effects directly through code. It runs locally on CPU as a CLI tool, Python API, and MCP server to evaluate audio and translate recordings into code.Agents https://github.com/N1nEmAn/sapper-v2https://scouthub.dev/en/news/2026-11-10/#r40Tue, 10 Nov 2026 06:00:00 GMTsapper-v2 is an orchestration harness that organizes swarms of AI agents with specialized roles to perform autonomous security penetration testing. It allows users to freely swap the underlying models, CLIs, and doctrines while maintaining shared memory and coordinated teamwork.Cybersecurity https://github.com/anonnerdfrenzy/survival-llmhttps://scouthub.dev/en/news/2026-11-10/#r39Tue, 10 Nov 2026 06:00:00 GMTSurvival LLM is a free, completely offline AI assistant and emergency library that runs entirely on your local computer without internet access. It answers questions using an offline database of medical and survival guides, showing the exact cited sources and its step-by-step reasoning for every answer.Data & search https://huggingface.co/LiquidAI/LFM3-1.7Bhttps://scouthub.dev/en/news/2026-11-10/#r35Tue, 10 Nov 2026 06:00:00 GMTIt supports a 256K-token context window and requires only about 1 GB of memory at 4-bit precision, allowing it to run smoothly on edge devices like phones and laptops.Models https://github.com/OpenEnvision/WorldFoundryhttps://scouthub.dev/en/news/2026-11-10/#r33Tue, 10 Nov 2026 06:00:00 GMTWorldFoundry is an open-source framework designed for reproducible inference and evaluation of generative world models across video, 3D/4D, and embodied action. It offers unified workflows with CLI and browser-based interfaces to inspect generated artifacts and track standardized benchmark metrics.Research https://github.com/anthropics/skillshttps://scouthub.dev/en/news/2026-11-09/#r29Mon, 09 Nov 2026 06:00:00 GMTThis repository provides structured folders of instructions, scripts, and resources that Claude dynamically loads to execute specialized tasks reliably. It includes demonstration skills for creative, technical, and enterprise workflows, as well as production-used tools for creating and editing documents.Agents https://github.com/jamiepine/voiceboxhttps://scouthub.dev/en/news/2026-11-09/#r27Mon, 09 Nov 2026 06:00:00 GMTVoicebox is a local-first, open-source voice studio that combines speech dictation and voice cloning across eight TTS engines directly on your machine. It ensures full privacy without relying on cloud services and allows MCP-compatible AI agents to speak using custom voices.Audio & video https://github.com/vercel-labs/agent-browserhttps://scouthub.dev/en/news/2026-11-09/#r26Mon, 09 Nov 2026 06:00:00 GMTagent-browser is a Rust-based CLI that allows AI agents to control web browsers through shell commands. It represents web pages as compact accessibility trees with element references, letting agents navigate and click elements step by step.Agents https://huggingface.co/facebook/sam3https://scouthub.dev/en/news/2026-11-09/#r25Mon, 09 Nov 2026 06:00:00 GMTThis model is designed for mask generation, video processing, and feature extraction. It is built for the Transformers framework and provided in the safetensors format.Models https://github.com/modelflare-ai/AnyModelBothttps://scouthub.dev/en/news/2026-11-09/#r32Mon, 09 Nov 2026 06:00:00 GMTAnyModelBot is an open-source, local-first desktop application that lets you run personal AI agents using models like GPT, Claude, and DeepSeek. It keeps your chat history, files, and API keys on your own machine while allowing bots to run commands, manage tasks, and connect via apps like Telegram and Discord.Agents https://github.com/Sandflow-ai/sand3dhttps://scouthub.dev/en/news/2026-11-09/#r30Mon, 09 Nov 2026 06:00:00 GMTIts entire API fits into a single prompt, references parts by name rather than coordinates, and exports directly to formats like GLB, URDF, and USD.Design & images https://github.com/shanselman/gputaskmanhttps://scouthub.dev/en/news/2026-11-09/#r28Mon, 09 Nov 2026 06:00:00 GMTA terminal-based GPU task manager that monitors per-process VRAM and engine activity across Windows, Linux, and macOS. It helps local AI users understand memory usage by breaking down allocations into loaded model files, weights, and KV caches.Tools https://github.com/netease-youdao/Confucius4-R2T2https://scouthub.dev/en/news/2026-11-09/#r31Mon, 09 Nov 2026 06:00:00 GMTThis is a low-latency streaming speech recognition model that commits transcribed text permanently without revising previous words, preventing visual flicker. By post-training only the language decoder, it achieves high real-time accuracy for live captioning, simultaneous translation, and downstream AI agents.Audio & video https://huggingface.co/Qwen/Qwen3.8-27Bhttps://scouthub.dev/en/news/2026-11-08/#r17Sun, 08 Nov 2026 06:00:00 GMTIt also features flexible thinking controls, allowing users to tune reasoning depth and retain reasoning context across interactions.Models https://github.com/ParadevAI/Paradevhttps://scouthub.dev/en/news/2026-11-08/#r22Sun, 08 Nov 2026 06:00:00 GMTParadev is a desktop application that allows developers to run multiple CLI coding agents in parallel using separate Git worktrees and branches. It integrates terminal sessions, code review, and browser previews into a single workspace powered by your own agent subscriptions.Coding https://github.com/meta/astryxhttps://scouthub.dev/en/news/2026-11-08/#r24Sun, 08 Nov 2026 06:00:00 GMTIt provides customizable theming without styling lock-in and allows teams to inspect or eject component source code directly into their projects.Design & images https://github.com/wangzan101/Mikahttps://scouthub.dev/en/news/2026-11-08/#r20Sun, 08 Nov 2026 06:00:00 GMTMika is an on-device AI agent for Android that operates apps and browses the web to complete tasks for you. It runs on a hidden background screen so you can keep using your phone normally, keeping your data local without relying on external project servers.Agents https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017https://scouthub.dev/en/news/2026-11-08/#r18Sun, 08 Nov 2026 06:00:00 GMTDeepSeek-V4.1-Flash-1017 is an updated multimodal model that enhances performance across reasoning, coding, and visual benchmarks.Models https://github.com/pipeshub-ai/pipeshub-aihttps://scouthub.dev/en/news/2026-11-08/#r19Sun, 08 Nov 2026 06:00:00 GMTPipesHub is an open-source enterprise search platform and context layer that connects business tools like Slack, Google Drive, and GitHub. It enables both teams and AI agents to query company knowledge with citation-backed answers that respect existing user permissions.Data & search https://github.com/qybaihe/blahttps://scouthub.dev/en/news/2026-11-08/#r23Sun, 08 Nov 2026 06:00:00 GMTBLA is a defensive security tool designed to protect software builds, binaries, and app bundles from AI-powered reverse-engineering agents. It works by injecting decoy data and exhausting the analyzer's token and resource budgets to induce hallucinations without altering the application's actual runtime behavior.Cybersecurity https://github.com/THU-Agent/Coca-colahttps://scouthub.dev/en/news/2026-11-08/#r8Sun, 08 Nov 2026 06:00:00 GMTThis project compresses retrieval and tool outputs into latent representations instead of feeding long, raw text into LLM contexts. It provides code for training, evaluation, and baselines like LLMSummary and LLMLingua to reduce context overhead in multi-turn agent interactions.Agents https://github.com/cloudflare/security-audit-skillhttps://scouthub.dev/en/news/2026-11-07/#r16Sat, 07 Nov 2026 06:00:00 GMTThis skill turns coding agents into security auditors by orchestrating a structured, six-phase audit workflow across codebases. It features isolated verifier agents that actively attempt to disprove candidate vulnerabilities before generating verified, machine-readable findings.Cybersecurity https://github.com/microsoft/VibeVoicehttps://scouthub.dev/en/news/2026-11-07/#r5Sat, 07 Nov 2026 06:00:00 GMTVibeVoice provides open-source voice AI models for both speech-to-text recognition and real-time speech generation. It supports streaming transcription, edge CPU inference, and structured long-form audio transcribing with speaker identification across multiple languages.Audio & video https://github.com/deepseek-ai/dsh-superagent-prototypehttps://scouthub.dev/en/news/2026-11-07/#r2Sat, 07 Nov 2026 06:00:00 GMTThis is a research prototype of a proactive coding agent that monitors a GitHub repository and executes development tasks, such as opening pull requests, when asked by authorized users. It is designed to minimize demands on human attention by acting only when permitted, and it provides a web panel to track items requiring human review.Coding https://huggingface.co/Lightricks/LTX-2.5https://scouthub.dev/en/news/2026-11-07/#r1Sat, 07 Nov 2026 06:00:00 GMTThis diffusion model supports multimodal generation and conversion across text, image, video, and audio. It allows users to perform tasks such as text-to-video, image-to-video, and video-to-audio transformations using a single model file.Audio & video https://github.com/NVIDIA/auto-ontologyhttps://scouthub.dev/en/news/2026-11-07/#r4Sat, 07 Nov 2026 06:00:00 GMTAuto Ontology is an open-source Python framework that builds a semantic context layer from enterprise metadata to help AI agents reliably query databases. It translates natural language into SQL, validates queries against certified definitions, and serves context via MCP, CLI, and APIs.Data & search https://github.com/microsoft/TokenEconomizerhttps://scouthub.dev/en/news/2026-11-07/#r7Sat, 07 Nov 2026 06:00:00 GMTTokenEconomizer is a plugin that reduces the cost of running coding agents by learning from past sessions in a repository without modifying the agent itself. It cuts waste by remembering repository facts, pruning unused tools, and stepping in when the agent gets stuck in failure loops.Coding https://github.com/onehumanbeing/esp32-iphone-agenthttps://scouthub.dev/en/news/2026-11-07/#r6Sat, 07 Nov 2026 06:00:00 GMTThis project allows OpenAI-compatible vision models to view and operate a real iPhone using a low-cost ESP32 board for screen mirroring and USB input. It enables the AI to tap, swipe, and type directly on the device without requiring a computer, jailbreak, or developer account.Agents https://huggingface.co/moonshotai/Kimi-K3.1-Prohttps://scouthub.dev/en/news/2026-11-07/#r3Sat, 07 Nov 2026 06:00:00 GMTKimi K3.1 Pro is an open-weight multimodal model with a 1-million-token context window designed for agentic tasks across text and images.Models