AI Frontend Governance
for production codebases.
When AI coding agents edit your UI, Decantr keeps every change inside your product standards.
Not a component library. Not a code generator. Typed contracts, route-scoped context, and evidence the agent can repair against.
How are you starting?
Attach Decantr to an existing app as a contract and evidence layer. No rewrite, no CSS takeover.
Start from a certified app kit, then own the contract as it evolves.
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.
The first AI pass can look good. The tenth pass is where teams lose coherence: duplicated components, inconsistent shells, route drift, stale docs, and visual decisions no one can audit.
Without Decantr · drift compounds
With Decantr · same contract, any theme
Adopt the app, load typed route context, let the agent edit, then verify with evidence before the change lands.
Decantr gives agents a typed model of the frontend they are editing, scoped context for the current route, and findings they can repair without parsing prose.
Markdown remains readable for humans. Agents get graph snapshots, contract capsules, and route-scoped context that point to the exact pages, shells, patterns, rules, and evidence in play.
MCP-native governance: agents can read the contract graph, prepare route-scoped work, verify findings, and request repair prompts.
Read the current design spec
Compact project readiness, pack, graph, and local-authority state
Load the cache-friendly typed Contract capsule for an agent session
Read graph metadata, route subgraphs, history snapshots, or typed snapshot diffs
Query current or historical typed graph nodes, relations, and endpoints
Traverse current or historical graph relationships from route, token, component, or rule nodes
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, starter kits, 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
Typed findings with stable codes, repair IDs, graph anchors, and optional prompts
Structured repair plan with action payload, evidence, read targets, constraints, and rerun commands
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
Generate the typed Contract graph, graph diff, manifest, and contract capsule
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 certified vocabulary across patterns, themes, shells, and starter kits
Full project audit — drift, packs, guard, critique
Aggregate Project Health across many Decantr projects
Bridge Decantr tokens into Tokens Studio-compatible JSON
Attach Decantr to the app you already have, give the agent route-scoped context, then verify the change before it lands.
Decantr inventories routes, framework, style signals, local docs, and existing UI patterns, then writes an observed contract you own.
Project Health emits stable codes, typed repair IDs, graph anchors, and evidence bundles; graph snapshots give the assistant replayable history to fix drift.
Project Health and MCP tools emit stable codes, typed repair IDs, graph anchors, and source evidence. The agent gets a precise finding instead of a vague review comment.
COMP001: local Button reimplemented instead of importing the project-owned primitive.CTX002: execution packs are missing, so agent context may be stale.ROUTE001: observed route is not represented in the contract.Button and removes the duplicate local primitive.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.
The public registry is a vocabulary source for patterns, themes, shells, archetypes, and starter kits. Your repo-owned Contract decides what applies; registry content never overrides local law.
Eight packages, one mission: make AI-edited frontend code reliable enough to govern.
Schema, validator, guard rules, and TypeScript types for the Essence format
Certified vocabulary contracts and discovery helpers for patterns, archetypes, themes, starter kits, and shells
Optional framework-agnostic CSS atoms runtime for starter kits and Decantr CSS adoption lanes
Execution-pack compiler primitives, typed Contract graph builders, graph diffs, and Contract capsules
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 typed graph context, Brownfield/Hybrid authority, local law, style bridges, Evidence Bundles, and repair prompts to AI assistants
Project Health, structured diagnostics, graph-anchored findings, component reuse drift, Evidence Bundles, CI schemas, and repair payloads
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.
Decantr stays useful across web stacks, but the governance path is getting deepest first for React, TypeScript, Tailwind, and shadcn-style component systems.
runnable adapter · generic-web contract-only fallback — your AI writes the runtime
Adopt a project, load route context, verify the edit, and keep the evidence.
Get Started