A free, MIT-licensed copy-paste library of 200+ production-ready React and Next.js components. Built with TypeScript and Tailwind CSS v4.

A vastly simpler way to do agent memory

Stop AI from building the wrong interface. Help AI agents understand the user’s work, choose the right interface, and repair what does not fit.

An open-source writing skill for AI agents and a private browser editor for clearer, more human prose without invented facts or flattened voice.

A free stock photography collection led by disabled creatives to help creative teams tell more authentic stories about disability.

Anthropic’s stage-by-stage playbook for the AI-native SDLC: how teams plan, design, build, test, deploy, and maintain software with Claude.

A complete interactive reference to every CSS measurement unit. From the basics of px and rem to the nuances of svh, dvh, and cqw.

Balsa UI is an agent-native, open-code component system for Vue and React.

How typographic grade preserves visual balance across screens and print substrates without altering layout geometry.

Free courses, tutorials, and use cases from Anthropic — whether you’re exploring AI, getting started with Claude, or rolling it out to your team.

Tired of Inter being everywhere? Two real criteria—cap-centered vertical metrics and a tall x-height—for choosing a UI font.

Detecting, extracting, and stylizing motion with WebGPU and TSL, covering motion masking, blob tracking, optical flow, and velocity-based motion blur.

A standard format for describing expected agent behavior for trace review and evaluation.

Now you can author skills for our agent, directly in Figma, to put your point of view to work. Here are 10 of our favorites to get you started.

Morph any SVG icon into any other with spring physics. Animate in React, Vue, Svelte, React Native, Astro or vanilla JS. Zero dependencies.

If you don’t want your AI agent to choke on your design.md, stop putting your entire design system into one file.

Liquid UI effects for React.

What Claude Code actually is, plus a plain-language decoder for the jargon around it. Models, tokens, agents, MCP, and friends.

A field study of how 20 open-source design systems and 6 platforms make themselves readable to AI agents.

A small library of extremely crafted, copy-paste components for chat agents, thinking states, human-in-the-loop approvals, and everything agents need.