A macOS workbench where Claude, Codex, and Hermes run on your specs, research, and Figma files.
Loading comments…
Project Info
Product Keywords
memi is a macOS workbench where Claude, Codex, and Hermes run on your specs, research, and Figma files. It's a signed native app that brings design-aware agent runs, project memory, and Figma/FigJam handoff into one desktop environment. Instead of scattering prompts across terminals and browser tabs, memi keeps the runtime, agent sessions, design artifacts, and run history local and inspectable.
Research, specs, tokens, decisions, and reviews live in one readable layer. Project memory is editable project state — not hidden prompt soup — so agents can read, diff, and reuse it across runs.
Start Codex or Claude Code with the right auth, permissions, and model settings. Every run produces a compact spine with prompts, plans, tools, files, and cost — expandable into a raw log when you need the details.
Pull tokens, components, trees, and screenshots from Figma when needed. The bridge runs as a local WebSocket server on port 9224, and you can export Mermaid and FigJam-ready planning source before any external sync.
memi carries taste as executable practice. Skills like UX_TENETS_TRAPS capture the screen, score tenets, catch traps, and turn critique into the next tweak. The default SUPERPOWER.md defines an autonomous design loop: OBSERVE → PLAN → EXECUTE → VALIDATE → ITERATE.
"AI design tools forget. memi keeps the product system readable."
Most AI tools treat context as disposable prompt filler. memi makes design memory a first-class artifact — plain Markdown and YAML that agents can read, diff, and reuse. The Figma bridge, skill files, and run receipts all feed back into that readable layer, so nothing gets lost between iterations.
You're a product designer or design engineer who wants AI agents to work with your design system, not around it. If you're tired of pasting Figma tokens into chat windows or losing context between Claude sessions, memi gives you a local, signed macOS app where the runtime, memory, and Figma handoff stay under your control.
Other tools you might consider
Emdash is an open-source desktop app for running multiple coding agents in parallel; one place to monitor sessions, review diffs, and turn issues into PRs.
You're running more coding agents than ever, but you can't keep up with them. That's where AgentPeek comes in. It pulls every session up into your Mac notch, live. Glance up, approve a prompt, watch token usage and manage the entire flow without pausing your YouTube video. All local, all yours.
Three things kept hitting me using Claude Code. Tab switching every 30 seconds just to check if it's still running. Claude silently blocking for 12 minutes while I was in another app. Coming back to find it finished or stuck 15 minutes ago. So I built CodeBreak. A pixel-art character walks your screen while CC runs. It celebrates when done, panics when it needs you, sulks on errors. $7 one-time. No sub. All future updates are free. Its for CC now, eventually will be Universal for all AI tools.
Tamamon is a macOS desktop pet that lives on top of your screen and grows the more you build with Claude Code. What it does: - 20 species to collect through a weekly gacha, each with its own evolved forms and quirks - Feed it, play (ball, bubbles), and decorate its habitat - Reacts to real time and weather — when it rains or night falls, your pet heads home to rest - Nothing leaves your Mac. No account, no sign-in, no tracking, nothing uploaded.
Maker
modemfox
Compare with
Alternatives
Loading comments…
