moooon
Motir
Vibe the project. Bring an idea — Motir's three AI layers plan it, track it, and ship it, end to end. You're looking at Motir, built in Motir.
- Vibe Project
- Open Source
- AI Agent
- AI Loop
- 6
- requests
- 4
- upvotes
- 501
- planned
- 4,797
- shipped
- (manual) In production, sync project MOTIR's runner groups once and read its `moooon-B-V` group back from GitHub — private repositories only, public refused
- "Grill me" is silently skipped: the sharpen_turn ask step comes back `unavailable` twice, and the failure is hidden once the run hands off to planning, so the plan is written with no question asked
- Live updates reach an open page by server push, not polling, on whichever instance holds it — Postgres NOTIFY fanned out across every `app` instance replaces the Workbench stream's per-tab watermark poll and the plan overlay's 2.5 s poll, one stream per tab, paused in a background tab, resuming after a drop without a page refreshmotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- Story E2E with acceptance video: one stream per tab, no timer polls, hidden-tab close and resume, offline Reconnecting and resume, no document load or RSC refreshmotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- Story test gate (integration): coverage floor, every-writer-heard, leak fixture, burst coalescing, one LISTEN session, missed-notification backstopmotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- useGeneratingPlanPoll: replace the 2.5 s timer with plan frames from the one tab stream, caller contract and existing tests keptmotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- Host-held stream client: close after the hidden grace period, reopen with the held cursor on show, reconnect with backoff after a drop, Reconnecting chip, en/zh stringsmotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- Plan frames on the same stream: watched-plan set carried on the stream, per-plan notification routing with the reader's read gate, frame carries plan id and reviewVersionmotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- Workbench stream route: replace the per-second watermark poll with hub notification, per-project coalesced re-read under the reader's context, 60 s backstopmotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- Per-process listener hub: one LISTEN on the direct URL, in-memory fan-out to open streams, bounded-backoff reconnect with a degraded log linemotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- NOTIFY triggers on every table the Workbench watermark and plan review read from, ids-only payload, plus a test that every input table has onemotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- (motir-core) Run the staging check on two `app` machines and read production and staging back from the platform — `fly machine list --json` showing two started machines, `fly secrets list` showing no `memory` store, the check's pass lines posted on the story with both machine IDs and the timemotir-core's web tier scales horizontally under agent traffic — each added `app` instance adds throughput (~500 req/s per instance, toward ~10k active agents), connections stay bounded, no reader is refreshed, measured first and proven by a re-runnable load test
- (decision) Planning capacity follows demand: two pools split by job kind, headroom scaling that wakes, creates and retires machines, a self-scaling graph service with a floor of 2, and a hard cost ceiling per pool and for the graph service. Amends MOTIR-7088 items 5, 7 and 8Planning capacity follows demand — a conversation turn never waits behind a planning run, the planning machines and the graph service grow and shrink on their own, and a load-tested cost ceiling is the only fixed limit
- Verify on production that motir.co/docs serves eleven languages after both deploys — a Japanese guide, Korean MCP tools from motir-core's localized catalogue, the French API and CLI notes, and a deep link under /plMotir in eleven languages — app.motir.co and motir.co in en·zh·ja·ko·de·fr·es·it·nl·pl·pt, per-language font sets, and work content in an org content language with per-user translation
- Verify on production that motir.co/ideas serves each idea translated in every language after the deploy and the owner's first fill runMotir in eleven languages — app.motir.co and motir.co in en·zh·ja·ko·de·fr·es·it·nl·pl·pt, per-language font sets, and work content in an org content language with per-user translation
- Verify on production that motir.co serves eleven languages after the deploy — detection, switcher, a localized 404, a tenant-host public project page, crawl data and per-locale fonts read on the live hostsMotir in eleven languages — app.motir.co and motir.co in en·zh·ja·ko·de·fr·es·it·nl·pl·pt, per-language font sets, and work content in an org content language with per-user translation
- The planner and agents write work content in the organisation's content language, while explanations and plan-session replies follow each person's own languageMotir in eleven languages — app.motir.co and motir.co in en·zh·ja·ko·de·fr·es·it·nl·pl·pt, per-language font sets, and work content in an org content language with per-user translation
- (motir-core) Story E2E: Chinese organisation, English-speaking planner and Korean member, approval and content-language changeMotir in eleven languages — app.motir.co and motir.co in en·zh·ja·ko·de·fr·es·it·nl·pl·pt, per-language font sets, and work content in an org content language with per-user translation
- (motir-core) Story integration test: both languages sent per job, proposal-to-approval language record across a setting change, explanation recording, agent prompt and project-state readMotir in eleven languages — app.motir.co and motir.co in en·zh·ja·ko·de·fr·es·it·nl·pl·pt, per-language font sets, and work content in an org content language with per-user translation
- (motir-ai) Story integration test: every writing job's assembled model request names both languages, missing language refused, preserved identifiersMotir in eleven languages — app.motir.co and motir.co in en·zh·ja·ko·de·fr·es·it·nl·pl·pt, per-language font sets, and work content in an org content language with per-user translation