A skill that turn any brand into a scrollable 3D world landing page

A language server for agent skills — /skill-name and $skill-name become real symbols

Framework for evaluating and improving agents

A benchmark built to evaluate and improve agent capabilities for supporting legal work.

A feed-forward 3D foundation model for reconstructing scenes from streaming data

slime is an LLM post-training framework for RL Scaling.

AI-first open source operating system for various devices, based on the Android.

Deterministic failure-mode scanner for TypeScript. Catches missing error handling around npm packages like Axios, Stripe, and Prisma before bad code ships.

The markdown editor for Claude & Codex

use.computer sdk

Harness for running and evaluating AI agents against RL environments

Puffing up reinforcement learning

Our library for RL environments + evals

100% private on-device voice models for speech-to-text and meeting transcription on macOS

Fast, accurate & comprehensive text measurement & layout

Expect tests your agent's code in a real browser

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

The agent that grows with you

An open source, self-hosted implementation of the Tailscale control server

Migrate to dench.com if you're reading this. Fully Managed OpenClaw Framework for all knowledge work ever. CRM Automation and Outreach agents. The only local productivity tool you need.

notch app for claude code & codex

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Embedded bash sandbox for agents, inspired by gVisor

Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

Control any computer remotely

Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Dock…

Runescape automation library, optimized for use by coding agents.

Retain is a native macOS application that aggregates AI conversations from multiple platforms into a unified, searchable knowledge base with intelligent learning extraction.

Anthropic's original performance take-home, now open for you to try!

Bootstraps a fresh Ubuntu VPS into a complete multi-agent AI development environment in 30 minutes: coding agents, session management, safety tools, and coordination infrastructure