The CLI for solo technical founders shipping weekly

Define · Develop · Deliver · Feedback · Iterate

Five commands. One weekly loop. Define the bet, build against it, ship, collect feedback, and decide the next move from your terminal.

$ npx loopkit init

Solo technical founders are strong builders but weak weekly shippers. The loop — define → develop → deliver → feedback → iterate — was designed for teams. Every tool handles one phase. None connects them from the terminal.

LoopKit connects them.

These commands support the loop, but they are not the product's center of gravity.

These commands work, but they are intentionally behind a flag. They may move out of labs as they prove useful, or be removed if they don't.

loopkit labs on   # enable all labs commands
LOOPKIT_LABS=1 loopkit radar   # enable per-invocation

Why are some commands in labs? The five core commands are the product. Everything else needs to earn its place by closing the loop, not by being a feature checkbox. See docs/MOAT.md for why we cut features.

# Start with an idea
loopkit init

# Add tasks and build
loopkit track --add "Build the landing page"
git commit -m "feat: add hero section [#1]"  # task auto-closes

# Collect feedback inline
loopkit pulse --add "The onboarding flow is confusing"
loopkit pulse --add "I wish I could export to Notion"

# Ship it on Friday
loopkit ship

# Review on Sunday
loopkit loop

Five questions. AI scoring. A brief that stings when it should.

• ICP score, Problem score, MVP scope score (each 1–10)
• Overall score — averaged anchor at a glance
• Riskiest assumption named explicitly
• One async validation action you can do tonight
• Sunday Reminder: Provides a helpful hint to set a recurring calendar event or cron job to close your week
• Friday Reminder: --cron flag installs a cron job that reminds you to ship every Friday at 4 PM
• Validation Mode: --validate flag runs a devil's advocate AI to stress-test your brief before building
• Shell Aliases: Prompted on first run to install shortcuts (lk, lks, lkl, lkt) for faster commands

• Tasks live in plain markdown (.loopkit/projects/[name]/tasks.md)
• Git hook auto-closes tasks when you reference [#N] in commits
• Stale task detection after 3 days — keep, snooze, or cut
• Snoozed tasks hidden until the snooze date, then resurfaced automatically
• Cut tasks archived to cut.md — never silently deleted
• Shipping score: tasks completed / tasks planned
• Daily Standup: loopkit track --stand prompts for your #1 focus today and logs it to track daily momentum
• Almost There Nudge: When shipping score is 50-70% with 2 tasks left, suggests completing them to hit 80%

• Reads your brief + completed tasks for AI context
• Generates drafts for Show HN, Twitter, and Indie Hackers
• Per-draft: use, edit in $EDITOR, regenerate, or skip
• Pre-launch checklist catches what you forgot (runs after draft generation to get to value faster)
• AI output remains calibrated by truncating long descriptions
• Auto-triggers celebrate confetti, but only if you actually use a draft
• Ship log saved to .loopkit/ships/YYYY-MM-DD.md

• Hosted Form & Widget: Collect feedback async via your own /pulse/[projectId] hosted page or an embeddable JS widget on your landing page. Fully supports offline submission with automatic real-time sync.
• Add responses from the CLI: loopkit pulse --add "user said this" (automatically deduplicates)
• Embeddable widget displays your actual projectId for easy copy-pasting
• AI clusters responses into: Fix now / Validate later / Noise
• Requires 5+ responses for clustering; shows raw list below threshold
• Tag clusters directly to your sprint

• Aggregates your week: tasks, ship logs, pulse feedback, and previous weeks' context
• Tracks your consecutive Loop Streak (e.g. 🔥 4 consecutive weeks) and acknowledges streak breaks
• LoopKit Score™: Aggregates shipping score, streak multiplier, and feedback into one 0-100 metric
• Proof Card: Generates a shareable, ASCII-styled terminal card that auto-copies to your clipboard
• Revenue: Log your weekly MRR with --revenue <amount>
• AI recommends the single highest-leverage thing for next week
• Smart Unstuck Mode: kicks in if you have 0 tasks, but only after your first week
• Context-aware upgrade prompts at week 4 or 8
• Override rate tracked — warns if you're overriding AI > 50% of the time
• Generates a build-in-public post (280-char checked)
• Async Mode: --async flag allows running loop any day within a 7-day window without breaking streak
• Milestone System: Detects and celebrates key moments (first week, month 1, first revenue, streak breaks, pricing signals)
• Referral Prompt: At streak ≥4, prompts to share LoopKit with friends for 1-month free credit
• One decision. One post. Week done.

• ASCII confetti burst for visual celebration
• Displays your shipping score, streak, and rank title
• LoopKit Score™ breakdown
• Revenue display if MRR > 0
• Shareable proof card auto-copies to clipboard
• Public Wins: --share flag posts your win to the public feed at loopkit.dev/wins for accountability and discovery

• Installs shell shortcuts for common commands (lk, lks, lkl, lkt)
• Supports zsh, bash, and fish shells
• Prompted on first run after loopkit init
• Remove with loopkit aliases --remove

LoopKit includes several features designed to build habits and drive retention:

• Milestone System: Automatically detects and celebrates 5 key moments (first week, month 1, first revenue, streak breaks, pricing signals) with encouraging messages
• Friday Reminder: Cron job (loopkit init --cron) reminds you to ship every Friday at 4 PM with terminal notifications
• Async Loop Mode: --async flag allows flexible scheduling without breaking your streak
• Almost There Nudge: Encourages completion when you're at 50-70% shipping score with 2 tasks remaining
• Referral System: Share your referral link (at streak ≥4) to earn 1-month free credits
• Public Wins Feed: Share your wins to the community for accountability and discovery
• Validation Mode: --validate flag runs a devil's advocate AI to stress-test your brief before building

All project data lives in .loopkit/ in your repo. No forced cloud sync. No vendor lock-in.

When you authenticate with loopkit auth, your loop logs and ship logs optionally sync to your web dashboard — so you can view trends, benchmarks, and share cards from anywhere. Local data remains the source of truth.

.loopkit/
├── config.json
├── projects/
│   └── [project-slug]/
│       ├── brief.md
│       ├── brief.json
│       ├── tasks.md
│       └── cut.md          ← cut tasks archived here
├── ships/
│   └── YYYY-MM-DD.md
├── logs/
│   └── week-N.md
└── pulse/
    └── responses.json

• CLI: Node.js 20+ · Commander · Clack
• AI: Vercel AI SDK · Claude (@ai-sdk/anthropic)
• Schemas: Zod (single source of truth in @loopkit/shared)
• Web: Next.js 16 · Tailwind v4
• Backend/Auth: Convex Database & Convex Auth

1. CLI-first, web-optional — developers live in the terminal
2. Async by default — no meetings, no community management
3. Opinionated over flexible — fewer decisions = more shipping
4. AI-augmented, not AI-dependent — degrades gracefully without a key

Built for solo technical founders shipping weekly.

The best time to ship was yesterday. The second best time is now.