Recently Evaluated

A React app that compares per-token prices across AI models and shows live or cached pricing from the LiteLLM Model Catalog API.

AX is a local router for coordinating coding agents across terminals and repositories. It gives sessions names, lets agents exchange messages on the same machine, and supports Claude Code, Codex CLI, Grok Build, OpenCode, and Pi.

An arXiv paper on detecting AI-generated commercial web content from structural signals rather than word-level text alone. The abstract reports a high-performing detector, attribution results, and released code and artifacts.

A Chrome extension that scores posts on X and LinkedIn, then blurs and stamps posts that cross a slop threshold. It uses your own API key with TypeSafe AI or OpenRouter and includes setup, settings, and privacy details.

ParseRail is an AI backend with 39 production endpoints for document parsing, extraction, redaction, contract analysis, and related business workflows. The page shows pricing, recorded calls, a playground, and code examples for using the API.

A command-wrapper tool that adds adaptive startup friction around agentic AI binaries like Claude Code or GitHub Copilot CLI, with Nix and non-Nix install paths and a stats command.

ContextIQ is a suite of AI engineering tools for inspecting context, agent workflows, protocol support, and payment or identity checks for AI systems. It includes inspectors for MCP/A2A/ARD, RAG chunking, traces, memory architecture, OIDC, DNS, x402, and ERC-8004.

An open, code-first fork of the Model Context Protocol focused on keeping the spec permissionless and transparent. The repo includes the protocol spec, schema, docs, compatibility notes, and build instructions.

Self-hosted voice agent runtime that streams speech-to-text, LLM output, and text-to-speech together in one process. The page shows quickstart commands, a minimal agent example, browser/client embedding, authentication notes, and performance benchmarks.

MineTrials is a benchmark-style writeup exploring how far AI agents can get in one hour of Minecraft, comparing models and harnesses and highlighting performance, cost, and a best run.

Self-hostable messaging workspace for AI agents and the people they work with. It positions agents as first-class members, with support for chat, email, and voice, plus Docker-based self-hosting and docs for getting started, CLI, and REST API.

A CLI and plugin bundle for AI agents to schedule social media posts through Postiz. It includes integrations for Claude Code, Cursor, Gemini CLI, Qwen Code, and DeepSeek Harness, plus support for the hosted Postiz MCP server.

A VS Code extension that turns codebases into an interactive call graph and exports compact execution context for AI assistants. It also helps review staged, branch, and PR changes by showing impact and blast radius.

Open-source Claude Skill plus MCP integration for job search and interview prep, with live job data, role-specific interview intel, answer scoring, resume scoring, and voice mock interviews as an upgrade path.

Event-driven API and CLI for watching live coding-agent sessions on a machine, with support for multiple harnesses and session inspection.

DrivingBench is a benchmark that tests frontier LLMs on real-world driving tasks in a Toyota Corolla with a cone course, leaderboard, run traces, and replay videos.

An open-source tool that screens AI agent tool calls and tool results before they are used. It works as an MCP proxy plus hooks adapter, with policy-based decisions, shadow mode, and local logging.

Open-source coordination protocol for coding agents that helps detect intent conflicts before code conflicts, built above Git and integrated with tools like Claude Code, Codex, and Cursor.

A Linear engineering write-up on speeding up CI for an AI-accelerated development workflow, with concrete changes to runners, checkout, test sharding, and setup costs.

A macOS menu bar app that shows Claude Code and Codex usage limits, reset timing, and usage status with native notifications and optional exact reset times.

Open-source checker that opens a generated web page in a real browser, inspects rendered controls, and runs mechanical checks without tests or an LLM.

A GitHub repo of skills for AI agents that help reduce generated UI and writing slop. It includes separate skills for UI and writing, plus install commands for common agent tools.

Jev AI is an interactive playground and API for typed AI decisions, with yes/no, choice, and scoring outputs plus confidence signals for routing, moderation, and other workflow decisions.

A Hugging Face dataset about an experiment in agentic autonomy protocols, built from output generated by Qwen 3.8 27B running autonomously on a single RTX 3090 for three weeks.