sarveshsea/memi

Memi

The design layer for agentic AI.

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, and file:line evidence 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

Then ask:

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.

Put the check on every pull request

Copy examples/github-actions/memi-design.yml into your repository as .github/workflows/memi-design.yml. The starter is pinned to the reviewed public Action commit and gives reviewers:

• a PR check that fails only on newly introduced interface debt;
• a memi-design-health artifact with the human-readable report; and
• SARIF annotations when the repository grants security-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 complete GitHub Action guide documents every input, output, permission, and evidence file.

One product layer, three surfaces

Surface	What it is	Status
Memi CLI	Interface intelligence and deterministic checks for local repositories, agents, and CI.	Available today
Memi Studio	A macOS workbench for bringing project context, agent workflows, and verification together.	Available today
Memi Canvas	A visual workspace for design-system context and controlled agent proposals.	currently in development

See the product

Memi Studio	Memi Canvas — in development
Bring an agent prompt, project memory, and a verification surface into one workbench.	Preview design-system context, inspect a proposal, and keep a human in the loop. This preview shows an active development build, not a released product guarantee.

What Memi adds to an agent workflow

Before the edit	During the edit	Before merge
Discover components, tokens, routes, states, and accessibility gaps.	Give the agent a scoped brief that names the system it must preserve.	Rerun deterministic checks and surface new interface debt in CI.

Need	Start with
Find UI risks and product-system context	audit-frontend-design
Plan a change around existing components and tokens	remember-design-system
Keep new interface debt out of pull requests	enforce-design-ci
Build and verify native Apple interfaces	build-swiftui-interface

Compatible with the shadcn registry and v0 design systems.

Evidence at a glance

The V15 confirmatory audit is a public technical disclosure, not a leaderboard. It separates receipt admission, rendered design quality, functional acceptance, and resource observations.

Measured record	Exact reading
36 / 36 frozen receipts admitted	Every preregistered agent cell had an auditable receipt. This is receipt admission, not universal performance.
10 complete model-graded matched pairs	Rendered design-quality comparisons that survived the prespecified screen. This is model-graded evidence, not independent practitioner review.
Buzzr / Expo: mean +1.4; Paraform / web: mean −0.4	The scoped non-inferiority gate passed on both graded task families. It does not establish general superiority.
0 / 21 corrected task-by-resource tests rejected	The study did not establish a speed, cost, or token-use advantage.

Separate historical release record: the 2.7 candidate record reported 2,187 / 2,187 tests passed. It is release evidence, not part of V15 and not proof that every project benefits.

Benchmarks and paper

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 the conference-style audit PDF, inspect the protocol and receipts, or review the V17 preregistration.

Memi InterfaceBench v1 is 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 remains not verified. Inspect the benchmark contract and workflow evidence.

Memi DesignWorkBench v2 holds 300 task contracts and requires practitioner calibration before any certification claim.

Prompts that map to real workflows

Goal	Copy-paste prompt	Supporting workflow
Establish a baseline before a UI change	Audit this frontend before editing it. Prioritize the five changes with the clearest file:line evidence.	audit-frontend-design
Turn evidence into a scoped plan	Turn the findings into a scoped UI change plan. Reuse existing components and tokens before editing.	remember-design-system
Protect a pull request	Set up a deterministic design CI gate for this pull request. Fail only on newly introduced interface debt and save SARIF plus the HTML report.	enforce-design-ci

Research, stated plainly

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.

Choose your integration

Surface	Start here	Best for
One-time CLI run	npx -y @memi-design/[email protected] diagnose . --no-write	Trying Memi without installing
Global CLI	npm i -g @memi-design/cli	Daily local use
Agent Skill	npx skills add memi-design/memi --skill audit-frontend-design	Codex, Claude Code, Cursor, and compatible agents
GitHub Action	Copy the starter workflow	Pull-request design CI
MCP server	memi mcp start --no-figma	Any MCP client
Studio	brew install --cask memi-design/memi/memi-studio	Supervised macOS workflows

GitHub Action

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 a memi-design-health artifact. Existing debt can be baselined while newly introduced debt fails the gate.

GitHub Action guide · CI recipes · current versions

Agent and MCP setup

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:

codex plugin marketplace add memi-design/memi --ref main --sparse .agents/plugins --sparse plugins/memoire

Agent stack guide · copy-paste recipes · full skill router

Trust and proof

• 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 in NOTICE.

Community

We welcome contributions. See CONTRIBUTING.md for setup and pull-request guidance. Bugs and feature requests belong in issues; questions and real project reports belong in Discussions.

Useful contributions include reproducible audit fixtures, framework adapters, skill improvements, accessible UI cases, motion checks, and before/after reports.

License

Studio interface references and adapted components include Hermes WebUI and the MIT Warp UI framework boundary around warpui_core and warpui; Warp AGPL application and client code is not copied into Memi.

MIT. See NOTICE for optional adapters and complete third-party attribution.