Recently Evaluated

A command-line tool for making yes/no, multiple-choice, and multi-level decisions in scripts and agent skills using decision models like Jev.

A llama.cpp fork that adds a JEV-compatible decision API for Choice, Score, and Noul evaluations while keeping standard LLM inference support.

A free AI usage and quota monitor for Codex, Claude Code, and Gemini CLI. It surfaces activity, remaining limits, reset timing, and trend views across desktop and mobile.

Meta AI research on RL-XAR, a method for training language models toward expert-level writing using expert-aligned rubrics and reinforcement learning. The page explains the problem, the rubric-learning loop, and experiments on paper sections, story writing, and Wikipedia-style text.

Open-source, self-hosted platform for running managed AI agents like Claude Code, Codex, Hermes, DeepSeek Harness, and Pi on infrastructure you control.

Open-source demo for recognizing hand-object manipulation stages in everyday video, with installation steps, run commands, and a short explanation of the pipeline.

An unofficial Claude client for Nokia Series 40 phones, paired with a small Go server that handles TLS, chat backend access, and device pairing.

Enterprise Postgres platform for AI apps, with managed, BYO cloud, and on-prem deployment options. It adds built-in MCP access for agents, pgvector and hybrid search for RAG, branching for isolated experiments, and a path from prototype to production.

OpenAPPA is an open-source deterministic guardrail and information-flow policy engine for LLM agents. The page describes flow-based security labeling, CI validation, remedy plans, sanitizers, authorities, and subagents, with links to docs, GitHub, Discord, and benchmark claims.

Anthropic’s documentation page on how to prompt Claude Opus 5.5, with guidance for effort calibration, agentic runs, progress updates, multi-app workflows, refusals, pasted text, and visual inputs.

Ceptile is an AI-powered web search and conversational research product with live web results, verifiable source citations, and a demo video on the homepage.

A Vercel tutorial showing how to wire Jev into a TanStack Start app using TanStack AI and the Vercel Gateway adapter, with typed decision routing and server-side validation examples.

A Vercel article showing how to use GPT-6 Sol with the AI SDK evaluation API to assess draft replies, score evidence-based answers, and read structured results in TypeScript.

Sandboxed macOS VMs with full Xcode for AI coding agents, plus a lightweight Linux container mode. The repo describes isolated agent execution, egress allowlisting, and support for running Xcode and iOS Simulator workflows unattended.

Windows UI Automation backend for computer-use agents, extending arc-cua with a JEV-driven decision loop for desktop tasks on Windows.

FDA is a developer tool for giving AI agents temporary, session-scoped access to machines with audit logs instead of standing SSH access.

A set of Claude Code skills for analyzing chess games with Stockfish-backed annotations, HTML viewing, transcription from think-aloud audio, and narrated video output.

Drawgent is a coding agent that works on a live Excalidraw canvas, aimed at turning sketches and diagrams into code. The page shows a real project with a README-driven quick start, demo section, setup command, and detailed notes on how the agent interacts with diagrams and code.

A blind listening arena for AI-composed music. Users compare two pieces against the same brief, vote A/B/tie/neither, and then reveal results and rankings.

An interactive site that maps your AI worldview and compares it with public figures and simulated users on how AI may change the future.

Technical research page for BlueVetaUpright, a product-photo orientation correction system. The page explains the problem, the system design, dataset methodology, and benchmark results, including comparisons against ChatGPT, Gemini, and Claude.

Open-source MCP-based relay for connecting a video game to AI agents, starting with World of Warcraft Classic Era. The repo describes the architecture, includes a self-host path, and splits components into SDK, WoW kit, platform, and bridge.

AI code security scanner that reviews a repository, flags exploitable issues, and provides a scoped fix prompt for each finding.

An offline hybrid retrieval engine for RAG that runs on-device, including phones. The repo shows BM25 plus dense retrieval, cross-encoder reranking, sparse expansion support, and bindings for Rust, Python, Swift, and Kotlin.