Skip to Content
v0.8.0 · shippedNative mobile SDKs, optional Sentry enrichment, and bring-your-own keys/storage. Read the changelog →

The comprehension layer for AI-built apps

Your AI wrote it. Mushi tells you why it broke.

Plain-English explanation of what broke, plus a fix you can paste into Cursor or Claude Code — so a bug costs five minutes, not your whole afternoon.

MIT-licensed SDKs · self-hostable · no second LLM key

  • License: SDKs MIT · server AGPLv3 · enterprise edition commercial
  • Self-host: Self-host the whole stack with one command.
  • No lock-in: Your reports, your keys, your repo — no lock-in.
  • Dogfood: Mushi runs on Mushi — we catch our own bugs with it.

60-second proof

npx mushi-mushi
Run the wizard. It detects your framework, installs the SDK, writes env vars, and prints the snippet. When something breaks in prod, the report lands in your queue with a plain-English read on the cause and what to change. Pull it into your editor over MCP.
npx mushi-mushi setup --ide cursor # then ask Cursor: "what's broken in prod?"

50 diagnoses/month on the free tier — no card. Self-host in under five minutes if you want.

See it in action

Admin console tour, SDK dogfood on glot.it, and theme-aware stills — click any frame to open the live surface.
Admin console · reports → fix timeline in the console · · open live demo ↗
SDK on glot.it · shake / tap to report from a real Thai-learning app · · open live demo ↗
Dashboard· theme-aware still · swaps with your system theme · · open live demo ↗
Report detail· screenshot + plain read + fix timeline · · open live demo ↗

What this is (and is not)

Built for solo founders who ship with AI and lose afternoons debugging code they did not fully write. Works inside your editor — not another dashboard. Sentry can plug in later; you do not need it to start.

Where to start

Pick the path that matches what you are doing right now — each card links to the right next step.

Try it

Classification lands in about 10 seconds today; we are chasing sub-10. Pick a starting point:

Where Sentry stops, this picks up.

QuestionSentry aloneMushi
What it seesErrors your code throwsFriction your users feel
What lands in your queueA stack traceA short user note plus the screenshot they were looking at
Repeat bugsEach one shows up as a new issueThe same broken button collapses to one row
What you learn from fixesNone — the next dev repeats the mistakePast fixes become rules your editor sees on the next PR (.mushi/lessons.json)
Closing the loopAssign a ticket and remember to updateAn optional draft PR you can merge or ignore
Reporter attributionAnonymous"Fixed by Kenji" in the changelog; SDK toast on next session
From your IDECopy the issue ID into CursorCursor reads the report + relevant lessons and proposes the diff
Where it runsTheir cloudYours, ours, or both

What happens after a user reports something

  1. Step 1User reportsSomeone shakes or taps instead of emailing support. Mushi saves what they saw and what they were doing.
  2. Step 2Plain readSeverity and cause in English your team already uses — not a raw stack trace.
  3. Step 3One rowTwenty reports about the same broken button collapse to one issue.
  4. Step 4Draft PROptional: an agent opens a PR. You merge, edit, or ignore it like any other.

See Concepts → Architecture for the wire-level sequence diagram and component-by-component spec.

Running this for a team?

Deeper setup (SSO, audit, adapters) lives in docs/operators  on GitHub — the landing page stays on the solo-founder wedge.