KeelenUse case · Claude Max
Use your Claude plan for reviewable roadmap work.
Connect a Claude Pro or Max subscription, or an Anthropic API key, to a project. Keelen turns your Requests into planned tasks. It makes changes in isolated runs. Then it returns pull requests and decisions for review. The roadmap can keep moving. Your plan's capacity and settings still apply.
Keelen also runs on other AI accounts. Bring a Claude Pro or Max login, or an Anthropic API key. A Codex login from your ChatGPT subscription also works, or an OpenAI API key. GLM takes a Z.ai API key, and Kimi takes a Kimi Code membership key or a Moonshot API key. For Grok, connect a SuperGrok sign in or an xAI API key. Choose an engine for each project. The Operator plan costs $79 a month. You get 1,000 iterations, 10 projects, 5 concurrent runs, and 5 scheduled projects on the 24/7 loop.
- Keelen uses the credential you connect. That provider bills and allows usage on its own terms. Those terms stay with that plan. Keelen's platform tier is separate.
- Wake up to tested pull requests with acceptance criteria. There is no chat transcript to replay.
- You can set controls per project. They include red first proof, adversarial review, and clean checkout tests. They also include required checks and a review window. Test evidence needs a verified test command.
- Switch a project between Claude Code, Codex, GLM, Kimi, and Grok. The roadmap stays.
Use the subscription you already have
Connect a Claude subscription or API key. Then send one Request and check its acceptance criteria. Keelen's platform tier is separate. Allowances and billing stay with that plan.
What a night on the loop looks like
The scheduler picks the top task from your roadmap. It boots a fresh single use VM and clones your repo. Then it works the task with Claude Code. A verified test command enables failing test proof and a clean checkout test run. Work returns through your PR or branch policy. It comes with acceptance criteria and review evidence. When a decision needs you, the loop raises it for review. Other eligible work can continue within your project's capacity and controls.
Controls depend on the project configuration
A separate adversarial reviewer examines the diff. Red first proof and a clean checkout test run need a verified test command. Gated auto-merge needs the configured checks and a review window. Choose manual merge to keep the final click. Or choose branch-only delivery. It works without a pull request.
Honest limits
Keelen asks instead of guessing. Unclear requests come back as clarifying questions. Your test suite sets the ceiling on autonomy. A repo with no tests onboards with an honest no test posture. That lasts until the loop's own PRs add a suite. Your plan's limits are respected too. When Claude reports a usage window, runs back off and retry on a budget. Those retries never count against your iterations.
Recommended plan
Operator: $79 / month
FAQ
Will Keelen burn through my Claude Max usage limits?
You decide how much capacity it gets. You hold the dials. Your plan tier caps concurrent runs. Scheduling is per project. You can pause one project or everything at any time. If Claude reports a usage limit during a run, the loop backs off and retries on a budget. Those retries never count against your Keelen iterations.
Does Keelen see or store my Claude credentials?
Your token is encrypted at rest. Its keys rotate on their own. The token goes only into the single use VM that runs your iteration. That machine dies when the run ends. Credentials on disk die with it. Revoke access anytime and the token is deleted at once. Keelen never resells tokens. Usage bills to your own Anthropic account.
Do I connect a Claude subscription login or an API key?
Either. The recommended default is a subscription token minted with Claude Code's setup-token command. The loop then runs on your Claude Pro or Max plan with no API charges per token. An Anthropic API key works too; usage then bills to your API account at cost.
Is Keelen Claude-only?
No. Connect Claude Code, Codex, GLM, Kimi, or Grok on your own supported subscription or API key. Grok accepts a SuperGrok sign in or xAI API key. Pick an engine per project and switch without losing your roadmap or history.