Your AI already knows your design system
Slipstream UI is the AI-first component system built for AI-assisted development. Every component ships a machine-readable spec, an MCP server that serves it, and a validator that keeps agents honest.
What makes Slipstream UI different?
Start building
Start building in minutes
One command scaffolds the theme, component directory and registry config. Then take the path that fits your stack — package imports or owned source.
- 01
Run the CLI
npx @slipstream-ui/cli@latest init adds the theme, the component directory and the registry config.
- 02
Pick components
Browse the catalog, then add source with the CLI or the shadcn-compatible registry. You own the files.
- 03
Install dependencies
The CLI reports peer packages. Package imports need only react and react-dom.
- 04
Set your theme
Edit the CSS variables or call createTheme() once; light, dark and presets use the same tokens.
- 05
Verify with your agent
Point Claude Code, Cursor, Copilot or Codex at the MCP server and run validate_usage before merging.
What is free
Everything in the open-source project is MIT licensed. No account, seat or paywall gates the components, CLI, registry or MCP server.
- Components
- MIT
- CLI
- MIT
- MCP server
- MIT
- Registry
- Public
- Templates
- MIT
- Account required
- No
If commercial support or hosted tooling is offered later, it will be announced separately and will not remove anything that is MIT today.
- components
- 113
- machine-readable specs
- 113
- MCP tools for agents
- 5
- false positives on valid usage
- 0
Measured on 100 reviewed cases: 65.7% structural recall, 100% precision, 0 false positives on valid usage. Benchmark methodology
Built for the way software is written now
Half your UI is written by models. Slipstream gives them something better than docs scraped from training data: a spec they can query, and a guardrail they can self-check against.
Machine-readable manifests
Every component ships a COMPONENT_MANIFEST: exact prop schema, defaults, anti-patterns, accessibility requirements, composition rules.
validate_usage MCP tool
Agents validate generated JSX against the manifest before emitting — hallucinated props and missing requireds can be caught, not shipped.
shadcn-compatible registry
Install real source files through any shadcn-compatible CLI, or use packages. Your codebase, your rules.
Fully stateless
No runtime lock-in. Bring any backend — Vercel AI SDK, LangGraph, or raw streams. Components render; you own state.
Accessibility, tested
jest-axe suites on every component, aria-busy streaming states, polite completion announcements, reduced-motion variants.
Themeable to the token
One createTheme() call emits every CSS variable. Radius, dark mode, instant switching — no rebuilds.
How your AI uses it
Three steps, no fine-tuning, no prompt incantations.
Connect
Point Claude Code or Cursor at the Slipstream MCP server, or serve llms.txt and the /llm markdown routes.
Query the spec
The agent calls get_component_manifest and get_usage_examples — exact props, defaults, anti-patterns.
Self-validate
Before emitting, validate_usage checks the generated JSX against the manifest and corrects hallucinated props.
The failure mode, caught
An agent guesses onSend validate_usage checks the manifest and refuses the snippet before it is written.
1. Hallucinated usage
<PromptInputonSend={handleSend}placeholder="Ask anything"/>
The prop does not exist, and the required onSubmit is missing.
2. validate_usage response
{"componentId": "prompt-input","valid": false,"usageCount": 1,"issues": [{"severity": "error","message": "Unknown prop \"onSend\" on <PromptInput> (usage). This prop does not exist in the manifest."},{"severity": "error","message": "Missing required prop(s) on <PromptInput> (usage): \"onSubmit\"."}]}
Trimmed for display; the tool also returns the manifest anti-patterns.
3. Correct usage
<PromptInputonSubmit={handleSend}placeholder="Ask anything"/>
Validated against the same contract your docs, MCP server, and registry serve.
Measured on 100 reviewed cases: 65.7% structural recall, 100% precision, 0 false positives on valid usage. Read the methodology
Themes that ship with the library
Default, Violet, and Zinc presets included. Switch below — this is live theming, not a screenshot.
How it compares
Other libraries document for humans. Slipstream documents for both of you.
| Capability | Slipstream | shadcn/ui + AI Elements | assistant-ui | MUI |
|---|---|---|---|---|
| Distribution model | npm packages (ESM + CJS) | copy-in source via CLI | npm packages | npm packages |
| Components shipped | 113 (96 UI + 17 AI) | UI primitives + AI Elements | Chat surface + primitives | Broad UI set, no chat |
| Per-component machine-readable spec | Yes — props, a11y, anti-patterns | Partial — registry.json (files, deps) | No | No |
| MCP server | Yes — 5 tools incl. validate_usage | Partial — browse/search/install | No | Partial — agent skills |
| Validates generated JSX against the spec | Yes — validate_usage | No | No | No |
| llms.txt | Yes | Yes | Yes | No |
| Canonical markdown per component/page | Yes — /llm/*.md | Partial — MDX in repo | Yes — .md pages | No |
| AI chat components | Yes — 17 built-in | Yes — AI Elements (separate) | Yes — core focus | No |
| State & transport | Stateless — bring your own | Components only | Runtime adapters (AI SDK, LangGraph, custom) | n/a — no chat components |
| Styling | Tailwind + CSS variables | Tailwind + CSS variables | Tailwind | Emotion + theme object |
| Theme presets | 4 (Default, Dark, Violet, Zinc) | CSS-variable themes | CSS variables | theme object |
| Peer dependencies | react, react-dom | react | react | react, @emotion/react, @emotion/styled |
| License | MIT | MIT | MIT | MIT |
Reflects each project public documentation and published packages as of November 2026 · ✅ provided · 🟡 partial or a different model · — not provided for this purpose
Choose Slipstream
When agents must generate correct, design-system-compliant code and you want a validator in the loop before code ships.
Choose shadcn/ui + AI Elements
When maximum ecosystem gravity and copy-in ownership of a very large primitive base matter most.
Choose assistant-ui
When you need a battle-tested chat runtime: streaming, tools, and generative UI as the core product.
Start from a template
Complete, copy-paste patterns built entirely from Slipstream components.
For agent builders →
Wire the MCP server into Claude Code or Cursor, run validate_usage before emit, or serve llms.txt and markdown routes — five tools, three consumption paths.
For product teams →
Ship the production chat surface — streaming markdown, stop-generation, citations, approvals — with stateless components, jest-axe coverage, and your own backend.
Questions developers ask first
The short answers, with links to the pages that go deeper.
- Is Slipstream UI free?
- Yes. The packages, CLI, registry and MCP server are MIT licensed. There is no paid tier today and no account requirement.
- How is this different from shadcn/ui?
- shadcn gives you source you own. Slipstream adds a machine-readable manifest per component, an MCP server, and validate_usage, so an agent can read the contract and check generated JSX. The registry and CLI copy source the same way.
- Does it work with my stack?
- React 18 or 19 with Next.js App Router, Next.js Pages Router, Vite, Remix or Astro. Tailwind CSS 3.4, Tailwind 4, or the prebuilt stylesheets. The compatibility page records what is tested.
- What does validate_usage actually catch?
- Unknown props, missing required props, invalid enum values and documented composition violations. It is static: it does not prove runtime behaviour, visual correctness or WCAG conformance.
- Do I need an MCP client?
- No. Docs, copy-paste, the registry and package imports work without an agent. MCP is optional and additive.
Ship AI interfaces faster
113 components · 113 machine-readable specs · validate generated usage before it ships.