Memi
About
Agent design CI with four installable skills and 47 MCP tools for frontend audits, design-system memory, Tailwind, shadcn, Figma, accessibility, and spec-first UI creation.
Details
- Author
- sarveshsea
- Categories
- Design
Jump to
Setup
Install Memi in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/sarveshsea/memi
Follow the installation instructions in the repository README, then restart your MCP client.
Give your coding agent an interface brief before it edits. Memi maps the UI already in your repository, surfaces file-anchored accessibility and design-system risks, and gives you a deterministic check to rerun before merge. Start with the CLI, then add the same gate to every pull request.
Memi Studio is available today; Memi Canvas is currently in development. No account, API key, Figma file, global install, or daemon is required for the first audit.
Start with your next interface·Get Memi Studio·Read the research
Quickstart: find your first interface issue
Run one non-destructive audit in any frontend repository. It needs no account, API key, Figma file, global install, or daemon.
npx -y @memi-design/cli@latest diagnose . --json --no-write --fail-on none
The result carries normalized finding IDs, confidence, provenance, andfile:lineevidence so an agent can act on a specific finding instead of guessing.
Give the same context to your coding agent:
npx skills add memi-design/memi --skill audit-frontend-design
Audit this frontend before editing it. Prioritize the five changes that will matter most to users, reuse the existing system, and verify the result after the patch.
If Memi catches a real interface issue in your project,share the finding. Real reports are the most useful signal for what to improve next.
- a PR check that fails only on newly introduced interface debt;
- amemi-design-healthartifact with the human-readable report; and
- SARIF annotations when the repository grantssecurity-events: write.
The workflow does not need an API key or a Memi secret. Fork pull requests still receive the check and report; SARIF upload is skipped automatically when GitHub does not grant that permission.
If you prefer to configure it by hand, the completeGitHub Action guidedocuments every input, output, permission, and evidence file.
Compatible with theshadcn registryandv0 design systems.
Separate historical release record:the 2.7 candidate record reported2,187 / 2,187tests passed. It is release evidence, not part of V15 and not proof that every project benefits.
Quality non-inferiority passed for the scoped Buzzr and Paraform task families. The full paper reports exclusions, failed paths, and limitations without imputation.No superiority, speed, or dollar-savings claim is made.Read theconference-style audit PDF, inspect theprotocol and receipts, or review theV17 preregistration.
Memi InterfaceBench v1is a 100 target tasks specification with 5 pinned seed tasks; it is not an aggregate performance score. The historical candidate record reported 2,187/2,187 tests and 70.57% statements coverage. The greater-than-25% claim remainsnot verified. Inspect thebenchmark contractandworkflow evidence.
Memi DesignWorkBench v2holds 300 task contracts and requires practitioner calibration before any certification claim.
The research is disclosure material, not a product leaderboard. It keeps functional, rendered-quality, and resource evidence separate so a result cannot be made to say more than the study supports.
name: design on: [pull_request] permissions: contents: read jobs: memi: runs-on: ubuntu-latest permissions: contents: read security-events: write steps: - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 with: fetch-depth: 0 - uses: memi-design/memi@5fcbf39e1255af0c14c5a17ba6bde8cf1206e525 # v2.7.9 with: version: "2.7.9" report: true upload-sarif: true
The Action adds code-scanning annotations, a step summary, and amemi-design-healthartifact. Existing debt can be baselined while newly introduced debt fails the gate.
GitHub Action guide·CI recipes·current versions
memi agent install codex --project . memi agent install claude-code --project . memi agent install cursor --project . memi agent install grok-build --project .
{ "mcpServers": { "memoire": { "command": "memi", "args": ["mcp", "start", "--no-figma"] } } }
codex plugin marketplace add memi-design/memi --ref main --sparse .agents/plugins --sparse plugins/memoire
Agent stack guide·copy-paste recipes·full skill router
- Release gates— package, provenance, clean-install, MCP, plugin, binary, and public-surface checks.
- Current release truth— the public versions for CLI, Studio, and website.
- Reproducible case studies— pinned evidence, abstentions, and paired protocols.
- Dependency trust ledger— direct dependency purpose, dynamic boundaries, and review policy.
- llms.txt— compact machine-readable product map.
Memi has no npm install-time lifecycle scripts, no source upload or covert telemetry, explicit Figma connection, agent-kit--dry-run --json, immutable Action pins, and documented third-party boundaries inNOTICE.
We welcome contributions. SeeCONTRIBUTING.mdfor setup and pull-request guidance. Bugs and feature requests belong inissues; questions and real project reports belong inDiscussions.
Useful contributions include reproducible audit fixtures, framework adapters, skill improvements, accessible UI cases, motion checks, and before/after reports.
Studio interface references and adapted components include Hermes WebUI and the MIT Warp UI framework boundary aroundwarpui_coreandwarpui; Warp AGPL application and client code is not copied into Memi.
MIT. SeeNOTICEfor optional adapters and complete third-party attribution.
A lightweight MCP (Model Context Protocol) server for Blender. It offers a natural language interface with Blender’s Python API, improving access to documentation, and allowing users to explore and understand complex setups.
The Lottie Creator MCP brings your AI assistant directly into your animation workflow — giving it full access to LottieFiles Creator so it can build and edit Lottie animations on your behalf through natural language.
AI Video, Image & Audio Generation with over 150 models
Rive MCP let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of states/layers, Layouts, Shapes, and more.
Create, edit, and export SVGator animations (SVG, Lottie, GIF, video) from your AI assistant, and keep an editable project you can open in the editor anytime.
You're agent can Chain 60+ AI image and video models on one workflow canvas
Real interaction references and motion recipes for AI coding agents.
Search 1,145 real website designs by style, font, colour, section and measured design tokens.
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
MCP bridge between an AI agent and a live Aseprite session, same machine or agent-in-a-VM
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
