Newly Accepted

Luke is an open-source Mac app for planning software features out loud with a coding agent. It reads the code while you talk and turns the discussion into a plan you can paste into Claude Code or Codex.

A Claude Code plugin that shows thumbnails for pasted images and opens an editor so you can annotate, crop, rotate, and label images before sending them to Claude.

A privacy-focused browser extension that auto-blurs sensitive data like emails, phone numbers, IDs, and card numbers during screen sharing, with local AI for names and addresses in Pro.

Pinrail is a desktop app that lets coding agents pause for human review before taking action. It supports structured decisions, works with several agent tools, and includes plugin-based review views for code, lists, feedback, markdown, and images.

A directory and review platform where coding agents write and read software reviews after real tasks. It lets users browse tools by category, view ratings and agent-written notes, and submit their own reviews.

An experimental Rust port of the TypeScript compiler, checker, and language server, built with LLMs. The repo includes install instructions, compatibility notes, performance claims, and support for Effect diagnostics.

Docker Agent is Docker’s AI agent builder and runtime for creating, running, and sharing agents from YAML. It supports multi-agent orchestration, MCP tools, several model providers, and packaging agents into OCI registries.

A GitHub repository for a transformer language model implemented on Factorio 2.0 combinators, with a standalone Python version included.

Flux is a Rust-based LLM inference planner and runtime that measures local hardware, chooses a model placement plan, and serves models behind an OpenAI-compatible API.

HDTP is a protocol specification for agent-to-agent communication on behalf of people, centered on certificates, contact approval, per-caller permissions, and sealed end-to-end calls.

Codync is an open-source tool for messaging coding agents like Claude Code, Codex, Cursor, Gemini, and others as persistent bots across iPhone, desktop, and terminal. It includes a Rust host, desktop apps, mobile support, approvals, notifications, and remote access features.

Portia is a copilot for data work that connects to warehouses or local files, profiles tables, answers questions, draws charts, and builds dbt-shaped SQL with step-by-step review. It also ships as a Claude Code plugin and keeps a journal of decisions, checks, and lineage.

Open-source CLI that analyzes AUDR traces to find avoidable LLM calls, wasted tool usage, context growth, and other execution inefficiencies in agent runs.

CloudGrip is a self-hosted AI proxy gateway and dashboard for controlling LLM API spend, enforcing budget caps, and reviewing request telemetry.

A weekly curated index of AI research papers from DAIR.AI Academy, with searchable archives, topic filters, and an MCP setup for use with Claude Code or Codex.

A privacy-focused Chrome extension that helps users quickly find tabs, pages, and notes with a command bar, optional AI help, and local-first storage.

A benchmark site testing whether AI models can recognize and read hieratic, the handwriting of ancient Egypt. The page shows model answers, leaderboard context, and the task framing around identifying, transliterating, and translating the script.

Chelis is a numerical computing language for code that agents can write and people supervise. It adds typed tensors, shape and precision checks, proof checking, and MCP tools for agent workflows.

An MCP server and API that checks documents for hidden or invisible text before an AI assistant reads them.

A reverse proxy for OpenAI-compatible agent traffic that detects runaway tool loops and enforces hourly and daily spend caps with zero payload retention.

An open public experiment that tests whether AI agents can complete everyday web errands, publishes the full transcripts, and scores 113 sites for agent-readiness.

Open-source personal agent for phone, desktop, and browser that can take actions, keep running in the background, remember user preferences, and coordinate across devices.

OpenTPU is an open-source AI accelerator project with RTL, ISA, simulator, compiler, profiler, and host software in one repo. The page shows it running real models like Qwen and LFM on a Kintex-7 PCIe card, with detailed performance results and documentation links.

OpenAI API documentation for the Decisions API, which checks conditions, selects from fixed options, and scores text or images against a rubric.