AI decides what makes the list.

CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.

Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.

Anthropic’s Claude API platform for building AI products, apps, and agent workflows with Claude models, built-in tools, pricing tiers, and developer docs.

Yap is a private voice dictation app for Mac and Windows, with browser and mobile support. It recognizes speech on-device, types text at the cursor in any app, and is positioned for writing, chat, docs, and voice coding workflows.

Lumae is a free native macOS screen recorder and screenshot tool for polished demos, with automatic zooms, cursor smoothing, motion blur, captions, voiceover, and annotated screenshots. It also exposes editing commands over MCP so agents like Claude Code or Claude Desktop can edit projects directly.

AI operating system for private-market LPs that reads fund documents, tracks portfolio commitments, and checks fees and carry against LPAs with source-linked outputs.

AI resume reviewer that analyzes resumes for ATS compatibility, keyword use, and line-by-line editorial improvements. The page shows the core workflow, feature set, and a sample testimonial, making it usable as a public listing.

Meta AI Research post introducing Muse Realtime Avatar, a real-time system that turns Muse Realtime Voice into expressive, interactive avatars from reference media or images.

A local, offline AI assistant that runs on Mac or Windows and answers using a built-in emergency/reference library with source citations.

A browser-based showcase of nine classic demoscene effects implemented across thirteen languages, with pixel-identical output and side-by-side code comparison. It presents the code next to the rendered effect and highlights optimization steps, framed as a project built by an organization of AI agents.

Open-source AI workspace that combines agents, project chats, browser, terminals, files, and code review, with shared procedural memory via MuscleMemory for reusable skills across compatible agents.

BugTape is an error-tracking tool built for coding agents, capturing browser errors, failed requests, console output, and replay so an agent can inspect evidence and propose fixes over MCP.

A research code repository for studying how fine-tuning can trigger verbatim recall of copyrighted books in large language models. It includes preprocessing, fine-tuning, generation, and memorization-evaluation scripts, with setup notes and example data.

An AI model gateway for builders offering 35+ models through a single OpenAI-compatible API, with instant API key delivery and pay-as-you-go credits starting at €1.

A CLI for the Slack Web API built for coding agents. It exposes Slack methods through a single command format, supports JSON stdin, dry runs, pagination, and discovery commands, and installs via npm.

An open agent-identity protocol with a shipped reference implementation, TypeScript SDK, conformance test vectors, and protocol docs for identity, discovery, payments, and audit flows.

An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.

ArcNext is an Electron-based terminal emulator built for AI-assisted coding workflows, with Arc-style workspaces, split panes, an integrated browser, and an agent bridge for controlling browser panes from a terminal session.