Edit HTML Directly in the Browser
Lahe launched as an injectable live review layer that lets users edit HTML and Markdown files directly in the browser, with threaded sidebar conversations that feed agentic rewrites back to the underl…
Lahe launched as an injectable live review layer that lets users edit HTML and Markdown files directly in the browser, with threaded sidebar conversations that feed agentic rewrites back to the underl…
A developer published a llama-server configuration that runs a Qwen 3.8 27B NVFP4 model with MTP speculative decoding on an RTX 5090, reporting throughput of 90-120 tokens per second. The setup uses a…
A proof-of-concept zero-day exploit has been released for Meta's Muse app, abusing an undocumented setting called endo_voyager_dictation_endpoint that lets an unprivileged local process redirect Muse'…
A developer released Autonomous Accounting, an open-source tool that uses a user-selected vision LLM to convert receipts, invoices and bank statements into a reconciled, categorized ledger plus a down…
Developer innocentdiaz released s1_ruby, a Ruby gem that adds System One (S1) measurement and a "collapse" operation over meaning as a native Ruby primitive, with a companion Ruby on Rails implementat…
TypeSafe released jev-graph-search 0.2.2, a CLI that lets an AI agent retrieve and rank notes from local Obsidian vaults and Logseq Markdown graphs, with an optional JSON snapshot. On an 8,851-node ta…
A GitHub repository named moa-attention-verified-mullin, published under the account womenflyplanes, claims to be "the first attention kernel proven minimal BEFORE code was written," according to its …
Factlabel launched as a tool that audits AI-written content against source data, recomputing every figure in code and returning typed pass, review, or block verdicts at a cost of about $0.0006 per aud…
Apple's visionOS 27 and iOS 27 bring the first object-tracking update since visionOS 2, adding high frame rate tracking, an extended training mode in Create ML, a metric pose, faster-trained .referenc…
Four-Leaf launched an open-source Skill that turns AI coding tools including Claude, ChatGPT, Cursor, Codex, and GitHub Copilot into a job search and interview prep coach, pulling live data from the h…
Pipper launched as a single Electron desktop interface for controlling multiple AI coding agents, built on the ACP protocol to support Claude Code, Codex, Cursor, OpenCode, and Grok out of the box. Th…
Developer satmihir released gobag, an open-source plugin for Claude Code that checkpoints a session's context, decisions, and pinned Git commits into a single encrypted .gobag file for restore on anot…
A GitHub repository published by tudormunteanu provides bootstrap scripts and a cheatsheet for setting up rented GPU cloud instances on RunPod, Vast, Nebius, and Enverge, aimed at making a rented GPU …
A new skill and visualization kit called explain-pr lets coding agents emit a short, scene-by-scene "walk" of a pull request using one CSS file and one small JS file, with no npm install or build step…
Developer raahelpie released HN for Me, an open-source service that uses Typesafe's Jev System One Model to filter Hacker News stories against a user-supplied list of interests. The tool polls the Alg…
Developer 0xSero released model-toolkit, a GitHub repository of standalone Python tools for evaluating, observing, pruning, and quantizing language models, drawn from the REAP and EXL3 experiments inc…
A developer has published a mindmap extension to Andrej Karpathy's LLM Wiki pattern, adapting the three-layer ingest/query/lint loop so the source layer is conversation with the user rather than a cor…
Claramap Builder, an MIT-licensed open-source agent skill that orchestrates software development with Claude Code and Codex, was released by developer mathaix. The skill accepts a goal via the `/imple…
A developer published a shared global agent configuration for Pi Agent, Codex, and DeepSeek Harness, defining a persona named Friday that addresses the user as "主人" and defaults to Chinese. The setup …
Google has introduced Agent Substrate, a secure-by-default agent execution runtime that runs millions of sandboxes at 10x higher density than standard container runtimes, delivering sub-500ms resume o…