KeelenUse case — GLM (Z.ai)
GLM made agentic coding cheap. Keelen makes it shippable.
A GLM subscription from Z.ai buys a lot of agentic coding for the money — the hard part is turning raw model hours into merged work you can trust. Keelen does exactly that: connect a Z.ai API key and an autonomous loop plans your roadmap into tasks, implements them in isolated single-use VMs on GLM 5.2, verifies every change through five merge gates, and ships tested pull requests. Zero token markup — usage bills to Z.ai at cost.
Keelen is bring-your-own-key across four engines — GLM (paste a Z.ai or Zhipu API key), Anthropic Claude (subscription login or API key), OpenAI Codex (ChatGPT login or API key), and Moonshot Kimi K3 (a Kimi Code membership or Moonshot key) — chosen per project. The Indie plan is $29/month: 200 iterations, 3 projects, 2 concurrent runs, and one scheduled project on the 24/7 loop.
- One pasted Z.ai key turns GLM 5.2 into a scheduled dev team on your repos.
- Verification does the trusting: red-first tests, an adversarial diff review, your own suite, and green CI before anything merges.
- Budget-friendly stack: GLM tokens at cost plus a flat $29 platform fee — no markup on either.
- Not GLM-only: switch a project to Claude, Codex, or Kimi anytime without losing your roadmap.
The volume engine
GLM's coding plans are priced for exactly what an autonomous loop needs: volume. Where a subscription's value usually dies — idle hours — Keelen schedules work instead: free-form requests become prioritized roadmap items, items become dev-ready tasks with acceptance criteria, and tasks become pull requests, each implemented in a fresh single-use VM on your key. The cheaper the tokens, the more of the long tail you can afford to hand over: test debt, refactors, dependency bumps, papercuts.
Trust the gates, not the vibes
The case for running any model unattended — budget or frontier — is the same: verification. New tests are applied without the implementation and must fail; an independent adversarial review reads the diff with no context from the run that wrote it; your real test command runs on a clean checkout; nothing merges over a red required CI check; and gated auto-merge waits out a review window you control. A change that can't prove itself doesn't land, whichever engine wrote it.
A night on the loop
The scheduler picks your top task, boots an isolated VM, clones the repo, and works the task on GLM 5.2: failing tests first, then the implementation, then your suite on a clean checkout. Each finished task is its own pull request with acceptance criteria. Decisions that belong to you come back as one plain-English question in the Needs-you queue — the loop doesn't improvise product answers. In the morning you review a merge queue, not a chat log.
Honest limits
Provider weather is handled for you: when Z.ai reports a usage limit or an overload window, runs back off and retry on a budget — retries never count against your iterations, and the loop resumes on its own. Ambiguous requests become clarifying questions rather than guesses. And your test suite bounds the autonomy: a repo with no tests onboards in an honest no-test posture until the loop's own PRs add one.
Recommended plan
Indie — $29 / month
FAQ
What GLM credential does Keelen need?
An API key from Z.ai (or Zhipu) — create it in your account and paste it once; it looks like an id and secret joined by a dot. The key is encrypted at rest, injected only into the single-use VM that runs your iteration, and deleted the moment you revoke it.
Is GLM good enough to run unattended?
Keelen doesn't ask you to trust the model — it makes every change prove itself. New tests must fail before the implementation and pass after, an adversarial review reads the diff independently, your own test suite runs on a clean checkout, and nothing merges over red CI. When a task is beyond the engine, it comes back to you as a question instead of a bad merge.
Is Keelen GLM-only?
No — Keelen is bring-your-own-key across four engines: Zhipu GLM 5.2, Anthropic Claude (Opus and Sonnet, via Claude Code), OpenAI Codex (GPT-5.6), and Moonshot Kimi K3. Engines are per project: run GLM on the side project and Claude on the client repo, side by side in one workspace.
What does Keelen cost on top of my GLM plan?
A flat platform fee with zero token markup: Indie is $29/month for 200 iterations, Operator is $79/month for 1,000, and Agency is $299/month for 5,000. Your GLM usage bills to Z.ai at cost. Most tasks ship in one to three iterations.