OpenAI's Model Training Acquisition Team requested that user Vandivier delete their repository, claiming the code is so poor it reduces average model performance by 91% and that its absence could have…
Developer i18n-agent released i18nstack, an open-source toolset that turns Anthropic's Claude Code into a localization team with CLI tools, slash commands, and 46 language-specific translation skills.…
The R-ebirth project released relm, an R package with a Rust native core that embeds llama.cpp to expose local LLMs as base-R objects, supporting loading, generation, embeddings, activation tracing, s…
A developer built Ved, a fully offline, self-hosted AI voice assistant that runs on consumer hardware with 12GB VRAM. The project aims to evolve into a server-client architecture for smart home integr…
Opendray, a self-hosted gateway for AI coding agents like Claude Code and Codex, allows users to run agent sessions on their own infrastructure and control them from web, mobile, or chat. The open-sou…
A new open-source tool called burn2kicad converts a text netlist and component assets into a KiCad project, enabling AI agents to generate PCB designs without handling KiCad's complex file formats. Th…
Jonathan Michael Langford is building Jack, a local-first autonomous agent designed to prioritize privacy and security. The project aims to move beyond chain-of-thought reasoning in AI development.…
N3MO, a deterministic code intelligence tool that parses source code ASTs into a queryable knowledge graph without embeddings or LLM calls, launched on Hacker News. It enables transitive dependency ma…
LingBot-World 2.0 (LingBot-World-Infinity) introduces unbounded interaction horizons, rapid 60fps 720p video generation, diverse interactive elements, and an agentic harness for world modeling. The re…
A developer released local-review, a single-user tool for reviewing git branches and exporting structured markdown reviews to coding agents. The tool combines a Go backend with a React frontend into a…
Probelock, a new open-source tool, provides a lockfile for LLM tool calling that records model capabilities and fails CI when a model or quant swap lowers scores. It derives probes from existing tool …
Greppy, a drop-in grep replacement with code-navigation subcommands for AI agents, improves agent accuracy on structural code questions from ~53% to ~87% while using fewer tokens. The Rust binary incl…
A developer created a detailed specification for a Work Log generator that automatically compiles engineering work from GitHub, Linear, and Notion into a structured document with themes, monthly timel…
A Rust rewrite of PostgreSQL called pgrust now passes 100% of PostgreSQL 18.3's regression tests, matching expected output across more than 46,000 queries. The project aims to make PostgreSQL easier t…
Atelier, a 30-second install tool that sits underneath Claude Code to reduce token waste, claims 30% savings on AI coding costs by providing better search, shorter file reads, compact command output, …
RightNow AI released Auto, a compiler that records LLM-agent behavior and compiles it into verified, capability-confined WASM binaries. The system uses a tiered runtime that falls back to a frontier m…
CI Forge, a zero-dependency CLI and GitHub Action, replaces 20 CI services by running complete CI pipelines locally or natively within actions. It offers features like AI-powered code review, secret d…
Dream IDE, a desktop integrated development environment for managing multiple AI coding agents, has been released. The tool supports agent CLIs including Codex, Claude Code, OpenCode, and Cursor Agent…
Tilion released an open-source MCP server that gives AI agents like Claude Code a stealth Chromium engine to bypass web blocking systems such as Cloudflare, DataDome, and PerimeterX. The tool runs loc…
Anthropic published two official patterns to run its most powerful model, Claude Fable 5, at half the price by using cheaper models for routine work and reserving Fable for judgment calls. The advisor…