Visionaire MCP v0.7 introduces a verification layer that lets AI coding agents visually inspect live web pages, identify the exact CSS rule, file, and line causing rendering bugs, and verify fixes aut…
A developer released a starter kit for running ONNX Runtime Web inside a Web Worker to keep browser-based machine learning inference off the UI thread, improving performance on mobile devices. The pro…
Snitch, an open-source deterministic prose claim verifier for AI coding agents, has been released. It monitors transcripts from tools like Cursor and Claude Code to flag false claims made by AI agents…
Async Innovator released Hallint, a static analysis tool that lints AI-generated code for security vulnerabilities such as hardcoded secrets, SQL injection, and missing authentication. The tool, avail…
Researchers introduced negative squaring, a pre-tilting technique that adjusts weights against expected rounding errors before quantization, achieving 77% error reduction in a toy recurrent network wi…
Robobun submitted a pull request to Bun that changes source content cloning from Latin-1 to UTF-8 in Rust transpiler cache-hit paths, adds a UTF-8 decoding helper for native module/CJS cache generatio…
Samchon released TTSC, a TypeScript v7 toolchain that includes a compiler-powered plugin system, a type-safe executor (ttsx), a lint tool (@ttsc/lint), and an MCP code graph (@ttsc/graph) that reduces…
An open-source desktop alternative to OpenAI Codex, called Open Science Desktop, has been released for macOS, Windows, and Linux. The tool provides a local-first, model-agnostic AI research workbench …
Voice-to-Md.dev released Speech-to-Markdown, a 100% local app for macOS and iOS that converts voice into structured markdown documents using whisper.cpp and a local LLM, with no cloud dependency. The …
OpenVole 4.5, a self-hosted agent operating system for running and managing AI agents on personal hardware, has been released. The platform is model-agnostic, supports peer-to-peer networking via Vole…
VideoDB released an open-source MCP server that records desktop workflows via native accessibility events and optional screen video, then compiles them into reusable skill files for AI agents. The too…
Crawl4AI, an open-source web crawler and scraper that converts web pages into LLM-ready Markdown, has released version 0.9.1 with 12 bug fixes. The tool, which has over 50,000 GitHub stars, is designe…
A developer released Qualify, an open-source agent that uses Claude Code to automate sales lead research, scoring, and contact discovery. The tool helps sales teams focus on high-potential opportuniti…
A new open standard called ADD (AI Device Description) enables IoT devices to publish a single JSON document at a well-known endpoint, allowing AI systems to read the device's capabilities, constraint…
Makoto is a plugin for Claude Code that intercepts the AI agent's tool calls and blocks those that fabricate evidence, weaken verifiers, or make unsubstantiated claims, enforcing honesty by checking t…
TinyToT, a lightweight inference server compatible with Ollama, achieves 97% accuracy on a 35-question benchmark spanning graduate-level science, medicine, law, finance, and software engineering witho…
Hypeplan, a new open-source tool by developer Martin Rue, converts markdown-based plans into ASCII keynote speeches delivered in the terminal. The tool uses OpenAI's API for script generation and text…
A developer released Jukebox, an open-source collection of color themes inspired by music cover art, expanding on the original black-metal-theme concept to cover multiple genres and artists. The proje…
Researchers at MIT developed Human Operator, a wearable system that uses voice commands and first-person vision to control electrical muscle stimulation (EMS) for human augmentation. The system won MI…
R3, a local code review tool for AI agents, launched on Hacker News. It enables developers to leave line-specific feedback on agent-generated diffs and documents, tracking comments to resolution outsi…