Tools we use.
A running list of the web apps, MCP servers, APIs, terminal utilities and open-source projects we use or keep an eye on.
Web Apps
02Hosted apps and dashboards we open in the browser.
HasBeenReleased
A live dashboard tracking AI model releases and versions.
MCP Servers
02Model Context Protocol servers and SDKs that plug into coding agents.
MCP-UI
An SDK for rendering interactive UIs inside MCP tools.
APIs
01Services we call programmatically.
CLI & Terminal
05Commands we run straight from the terminal.
RTK (Rust Token Killer)
A CLI proxy that compresses command output for AI agents.
CodeBurn
A local terminal dashboard for AI coding token costs.
SkillSpector
A security scanner that vets agent skills before install.
MarkItDown
A utility that converts many file types to Markdown.
Open Source
08Libraries, frameworks and projects we self-host or build on.
Webwright
A browser agent framework where the LLM writes Playwright code.
Scrapling
An adaptive Python web-scraping framework.
BillionMail
A self-hosted mail server and email marketing platform.
Karpathy Skills
A CLAUDE.md ruleset that sharpens how agents write code.
Ponytail
An agent skill that makes AI coding agents write far less code.
Headroom
A context-compression toolkit for AI agents and LLMs.
Builder.io Skills
A collection of composable skills for coding agents.