We don't care what you build with.
We care what you build.
Decantr is the evidence-backed reliability layer for AI-generated web applications.
Not a component library. Not a code generator. A contract the AI checks, proves, and repairs against.
How are you starting?
New project from a published app composition — theme, sections, voice, and personality baked in.
Attach Decantr to an existing app as a contract layer first. No rewrite, no CSS takeover.
Any attached project. Codify local UI law, then layer Decantr guidance deliberately.
Start a new repo with Decantr context, checks, and AI contracts while keeping your runtime choices open.
AI coding assistants have no memory of design intent. Every prompt is a fresh start. By prompt 10, your app looks like it was built by 10 different people.
Without Decantr · drift compounds
With Decantr · same contract, any theme
Scaffold a complete design system, then paste one prompt. The AI reads the context files and builds a visually stunning, production-quality app.
Three tiers of context, each more specific than the last. The AI gets everything it needs to build every page correctly.
Every section context is self-contained. The AI gets everything it needs for each page in one file.
Install once. Every prompt gets smarter.
Read the current design spec
Top-level scaffold context for the whole app
Scoped context for a specific app section
Page-scoped context for one route or page id
Read compiled scaffold, page, section, review, or mutation packs
Inspect shortlist, manifest, and showcase verification metadata
Hosted aggregate intelligence coverage without crawling the registry
Search patterns, archetypes, themes, blueprints, shells
Full pattern details with layout specs
App templates with page maps
Composed templates with topology, zones, and transitions
Pattern recommendations for any page description
Generate a design spec from a description
Apply structured updates to DNA or Blueprint
Resolve violations by accepting, scoping, rejecting, or deferring
Compile a hosted execution-pack bundle from an essence
Validate an Essence against the schema
Detect design-spec violations in code changes
Score generated code on treatments, decorators, motion, a11y, responsive
Schema-backed project audit against packs, guards, and drift
Local evidence bundle for AI repair loops and CI artifacts
Scoped repair prompt with exact finding evidence and rerun commands
Aggregate health for many attached Decantr projects in a monorepo
Run health, evidence, and the next repair prompt in one local loop
Resolve route-local Brownfield or Hybrid authority, local law, visual evidence, and theme inventory before editing
Manage your project from the terminal
Scaffold a new project from a blueprint
Regenerate context files from the essence
Add a new page to a section
Remove a page from a section
Switch to a different theme
Run the local reliability gate for humans, CI, and agents
Write a privacy-redacted Evidence Bundle for AI repair and CI artifacts
Rank patterns against route, file, source-code evidence, and accepted local law
Scaffold greenfield apps from natural language; attached apps are steered into task context
Analyze, attach, verify, baseline, and show the Brownfield operating loop
Explain app/workspace state, adoption lane, stale artifacts, local law, CI wiring, and the ordered next-step queue
Prepare route context, authority, local law, evidence, and changed-file impact before an LLM edits code
Run the non-mutating required automation gate with schema-backed artifacts
Turn local buttons, cards, forms, themes, evidence, variants, and starter rules into project-owned UI law
Search the registry across patterns, themes, blueprints
Full project audit — drift, packs, guard, critique
Aggregate Project Health across many Decantr projects
Bridge Decantr tokens into Tokens Studio-compatible JSON
Pick a blueprint, scaffold, build. Three steps to a production-quality app.
AI agent ops and eval workspace
Design intelligence registry
Incident and telemetry command center
Matchday operations and VOD review
Paste the generated prompt into Claude Code, Cursor, or any AI coding assistant. The AI reads your context files and builds a production-quality app.
decantr_critique grades generated code against the essence — treatments, decorators, personality alignment, motion, a11y, responsive. The AI iterates until the score is green.
d-surface. Raw Tailwind everywhere else.d-surface / d-interactive.luminarum-glass applied to cards. luminarum-glow on primary CTAs.prefers-reduced-motion.Brownfield adoption is a first-class path. Decantr inventories what you have, drafts an observed contract proposal, keeps existing code and styling authoritative, and gives your LLM a repeatable route context before it edits.
Runs the adoption workflow: analysis, observed contract proposal, deterministic acceptance or merge, hosted pack hydration when online, Project Health, and baseline. In monorepos, install at the workspace root and pass --project apps/web; app primitives keep that scope instead of falling back to the root. Visual evidence is an optional follow-up when the app is running.
Surfaces route-local context, page and section packs, screenshot references, Brownfield intelligence, theme inventory, accepted local patterns, accepted local rules, changed-file impact, and the active authority lane before the assistant edits code.
Use doctor when the next step is unclear, codify project-owned button/card/form/shell/theme law when you are ready for Hybrid, and run ci as the non-mutating pull-request gate. Accepted local-rule findings show up in CI with file and line evidence. Setup, task paths, health prompts, refresh summaries, token exports, custom themes, and suggestions remain app-scoped in monorepos.
Hybrid lets an attached app adopt selected Decantr or project-owned authority without handing Decantr the whole source tree. Start with local law, map hosted ideas into your own components, then tighten verification only where the team agrees.
Turn observed buttons, cards, forms, shells, theme variants, source evidence, confidence tiers, and token/class mappings into project-owned law before enforcing them. Suggest and CI surface those accepted laws as active authority.
Doctor says whether the app is contract-only, Hybrid local law, style bridge, Decantr CSS, or composition mode.
Task context includes source authority, style authority, active laws, style bridge mappings, and runtime boundary warnings before the LLM edits.
Bring registry guidance into local law as advisory context first. Add project-owned components, token/class recipes, variants, and exceptions before treating it as enforceable.
Browse Featured, Certified, All, and Labs blueprint cuts without exposing internal maintainer labels — or publish your own patterns, themes, and blueprints for others to use.
Eight packages, one mission: make AI-generated UI reliable enough to govern.
Schema, validator, guard rules, and TypeScript types for the Essence format
Content resolver and discovery helpers for patterns, archetypes, themes, blueprints, and shells
Framework-agnostic CSS atoms runtime for layout utilities
Design Pipeline IR engine -- the brain behind intent-to-composition
Privacy-preserving event contracts, clients, and analytics sinks
Workflow commands, project scaffolding, Brownfield activation, Hybrid authority lanes, doctor, CI, local law, style bridges, visual evidence, baselines, workspace health, and registry sync
MCP server exposing design intelligence and reliability tools to AI assistants, including task-time Brownfield/Hybrid context with authority, local law, style bridges, and change impact
Shared audit, critique, source-grounded interaction evidence, Evidence Bundle, CI report schema with style bridge summaries, and Project Health engine
Security reviews should inspect the installed npm surface, not internal release scripts or showcase fixtures. See the security and permissions matrix for filesystem, network, process, telemetry, hosted upload, and MCP write-tool behavior.
Patterns are framework-agnostic. Your AI assistant writes the code in whatever you're already using.
runnable adapter · generic-web contract-only fallback — your AI writes the runtime