Pricing

One bot. One billing line. Pick your scope.

Pricing is TBD while we tune for the beta. Join the waitlist to lock in the early rate on whichever tier fits.

Solo

For founders shipping alone.

TBD
billed monthly
Join the waitlist
  • 1 connected repo
  • 1 PM tool integration
  • Unlimited tickets / month
  • Test-driven workflow
  • R&D ticket mode
  • Visual spec attachments
  • Multi-seat collaboration
  • Private repo support
  • Self-hosted runners
  • SSO + audit logs
  • Priority support
Most popular

Team

For small teams that want guardrails.

TBD
per seat, monthly
Join the waitlist
  • Up to 5 connected repos
  • Unlimited PM tools
  • Unlimited tickets / month
  • Test-driven workflow
  • R&D ticket mode
  • Visual spec attachments
  • Multi-seat collaboration
  • Private repo support
  • Self-hosted runners
  • SSO + audit logs
  • Priority support

Enterprise

For teams with their own compliance bar.

Let's talk
annual contract
Talk to us
  • Unlimited repos
  • Unlimited PM tools
  • Unlimited tickets / month
  • Test-driven workflow
  • R&D ticket mode
  • Visual spec attachments
  • Multi-seat collaboration
  • Private repo support
  • Self-hosted runners (rolling out)
  • SSO + audit logs (planned)
  • Priority support
FAQ

Common questions.

Switch any time. Specship treats your PM tool as one connection — disconnect Linear, connect Jira, the bot picks up tickets from wherever it can reach. History stays with your repo.

Yes, on every tier. The bot operates as a contributor in your repo — the same permission model your team already uses. Nothing leaves your Git host except via approved PRs.

Verified end-to-end: TypeScript / JavaScript with Jest or Vitest. Strong support: Python with Pytest, Go with the stdlib testing package, Ruby with RSpec. Other languages work where Claude Code does — we just haven't put them through the full TDD loop yet. The agent reads your codebase first and matches your linter, test runner, and conventions.

Yes — and it's the default. The agent posts acceptance criteria and a test plan to the ticket, waits for you to approve, then implements. You can disable the gate per-repo.

Comment on the PR or the ticket. The agent reads your feedback, replans, updates the tests if needed, and pushes a new commit. Same loop until you merge.

Self-hosted runners are rolling out to Enterprise design partners — the goal is your code never leaves your VPC. SOC 2 Type II is in progress, no badge claimed until the auditor signs.