From ticket to reviewed pull request.
Free and open-source, on your machine.

no_human plans, codes, tests and reviews the work, then opens the pull request.

Install desktop app

Unbeatable quality that costs you less. Much less.

Without no_human

You know the loop. You ask for the change. It comes back confident and wrong in a way that takes longer to disprove than to write. You correct it. It apologises and does it again. And the whole time you are the one checking it ran the tests, followed the conventions, used the right skill, and did not invent an API that does not exist. That is not delegation. That is supervision, with extra steps.

With no_human

Deliver 10× while you focus on the bigger picture. Every ticket runs to a reviewed pull request on its own, in parallel.

What your team gets.

  • 10x shipped per sprint. Tasks run in parallel while your engineers stay on the work that needs them. Each one comes back as a reviewable PR.
  • Predictable cost. About a tenth of doing the ticket by hand, with a hard budget cap on every task - spend is bounded before a run starts.
  • Zero new infrastructure. It runs on the developer's machine, on SQLite and your existing git host. Nothing to deploy, nothing to upload.
  • The work arrives done. Planned, coded, tested - and already torn apart by an independent reviewer before you ever see it.
  • Reviews go fast. Every PR carries the reviewer's evidence, file and line for every claim. You check findings instead of spelunking a diff.
  • No babysitting. Add the task and let it run; review the result. If it's genuinely stuck, it asks you one specific question.

Plugs into what you already run.

Jira, Linear and monday.com

Tickets import as tasks; status syncs back to the board.

GitHub and GitLab™

PRs and MRs open on your own host; issues import as tasks.

Slack and Teams messaging

Notifications land in your channel when a task needs a human.

Jenkins® and CircleCI

Test layers can run on your CI, and the results gate the loop.

Powered by Claude

The engine underneath - on your own Claude credentials.

OpenAI Codex

A second engine option - on your own OpenAI account.

PRICING

Start free. Working in a team? What one run learns, every run knows. Want it shipping 24/7? Our cloud works while you sleep.

The local product is free forever. You pay when you want the team to share what it learns, or when you want the work to run on our infrastructure instead of your laptop. Inference is always billed to you by your own provider - we never resell it.

Free

Local
$0
Forever · no credit card
  • The whole loop - spec, plan, build, independent review, open PR
  • Runs on your machine, against your git host
  • Your own model credentials; nothing billed through us
  • Unlimited tasks, bounded only by your provider spend

Pro

Team brain
Flat per-seat subscription
Pricing announced at launch · never metered
  • Everything in Free - the local product does not change
  • A shared team brain: what one run learns, every run knows
  • Conventions, traps and past review findings carry forward
  • One flat price - nobody is billed for thinking harder

Max

Cloud
Cloud execution
Pricing announced at launch
  • Everything in Pro
  • Execution on our infrastructure instead of your laptop
  • Hand over the sprint, close the lid, come back to open PRs
  • Usage dashboard and per-team budget caps

Enterprise

Custom
Let's talk
Scoped to your environment
  • Everything in Max
  • Your own cloud, your own model accounts
  • SSO and SCIM provisioning
  • Audit trail and per-team budget policy
Book a technical review