Kitchen Rush, a new benchmark for evaluating large language model tool-calling, measures both accuracy and latency by simulating an Overcooked-style kitchen where thinking time directly impacts game p…
Topaz, a small Unicode-first programming language that compiles to Rust, has been released as an open-source project. The language features a locked v5.2 specification, agent-ready design, and produce…
A new open-source project called SAMF introduces machine-readable validation contracts for LLMs, translating MoSCoW prioritization into deterministic guardrails for multi-agent loops. The tool aims to…
A developer released FlashQwen, a from-scratch CUDA inference engine for Qwen3-8B, built with C++ and CUDA. The project is hosted on GitHub and aims to provide efficient inference for the Qwen3 langua…
A developer created a method to run multiple isolated Claude Desktop instances on macOS, each with a color-coded Dock launcher that focuses existing windows instead of spawning duplicates. The solutio…
The Agent Audit Trail Format (AATF) is an open specification for recording why AI agents make decisions, including alternatives considered, confidence scores, and rejected options. It provides a struc…
A developer released Pi, a coding agent that runs entirely on a local machine without API keys or cloud dependencies. Pi works with a local llama.cpp server hosting Google Gemma 4 models, enabling off…
Aspectarian, a personal Vedic astrology transit app for macOS, uses Claude to generate interpretations of active transit contacts based on a user's natal chart. The app computes Parāśaran dṛṣṭi and yu…
Researchers from Aalto University and the University of Waterloo introduced Locket, a feature-locking technique for large language models that enables pay-to-unlock schemes by restricting specific mod…
Developer Geoff McCaughan released Sidekick, a self-hosted AI agent platform with persistent memory and 70 MCP tools that can extend itself without code changes. The platform runs on a remote machine,…
A developer released an open-source CLI tool called whoburnedmore that aggregates token usage and cost estimates from AI coding tools like Claude Code, Codex, and Cursor into a single dashboard, and i…
Diffusion Studio released Text-to-Lottie, an open-source framework that enables coding agents like Claude Code or Codex to generate production-ready Lottie animations from text prompts. The tool suppo…
Imbue AI released Ratchets, a Rust-based progressive lint enforcement tool that allows codebases to contain existing violations while preventing new ones through a budgeted, ratcheting mechanism. The …
DeepFork is a new agent skill that reverse-engineers any open-source repository into a clean-room rebuild blueprint, allowing developers to reimplement tools in their own stack without copying code. I…
HashMeterAi, a free open-source tool, provides a private, offline dashboard that unifies real AI token usage across multiple coding tools including Claude Code, Codex, Kimi, and Qwen CLI. It reads loc…
A developer launched Zero Browser, a lightweight data-exchange platform that eliminates HTML, CSS, and JS by using common interactive elements like markdown, forms, and grids. The project aims to simp…
A developer built a Visual Studio extension that integrates Claude Code's CLI, adding native diff viewing with accept/reject functionality, automatic compiler error sharing, and a dockable panel for c…
Constellation Network released an open-source audit trail plugin for AI coding agents that records every session, tool invocation, and prompt exchange into a local SQLite database with SHA-256 hash ch…
Developer LeoTheAIDev released AltiVerse, an open-source simulation tool that forks a single decision into 2-4 alternate realities with up to 1,000 AI-driven agents to explore second-order effects. Th…
Phlox, an open-source self-hosted agentic web chat application, has been released on GitHub. It supports any model provider including AWS Bedrock and OpenAI-compatible endpoints, and features agentic …