Pay for the orchestration, not the tokens.
A flat platform fee for the rails. Bring your own agents and LLM keys, run them on your own machines, and keep the freedom to switch models anytime.
Start freeFree forever on one repo and one worker. No card required.
Wire up one repo and one worker and watch a governed pipeline ship on your own code. No card.
- 1 solution, single repository
- 1 connected worker
- 1 user
- 3 concurrent stages
- Full triage → merge pipeline
- Configurable workflow & human gates
- Community support
For the solo builder running real, multi-repo work across their own machines.
- Up to 3 solutions, multi-repo
- 2 connected workers
- Up to 5 users
- 5 concurrent stages per worker
- Bring your own agent & LLM keys
- Reconciler: lost & stale-worker recovery
- Failure-aware routing & rework loops
- Email support
For a team that wants coordinated, auditable delivery with room to grow.
- Everything in Starter
- Unlimited solutions & repositories
- 5 connected workers
- Unlimited users
- Unrestricted concurrency
- Full attempt-level audit trail
- Priority support
A solution is one governed pipeline — its repositories, its workflow, and the workers that run it. Every paid tier is a flat platform fee: you bring your own agent subscriptions and LLM keys, and pay us nothing for tokens.
The real alternative is building it yourself.
| IssueFlow | Building it yourself | |
|---|---|---|
| Routing and stages | Built in — stages, outcomes, fail reasons | Scripts and CI glue you maintain |
| Human decisions | Gates anywhere, one Waiting-on-you queue | Ad-hoc pings and PR comments |
| When an agent gets stuck | Pauses, asks, escalates up your ladder | You notice, then you restart it |
| Lost or stalled workers | Detected and recovered automatically | Found when something looks quiet |
| Audit and cost | Every attempt, outcome and token recorded | Whatever your logs kept |
| Agents | Five bundled, plus scripts — per stage | Whatever you wired up |
Questions
Do you charge for tokens or LLM usage?
No. You bring your own agent subscriptions and LLM keys and run them on your own workers. IssueFlow charges a flat platform fee for the orchestration — never a markup on your model usage.
How is billing handled?
Subscriptions are managed through Stripe, monthly or annually — annual bills at ten months' price. The portal routes you to Stripe to start, change, or cancel a subscription; the free tier needs no card at all.
Where does my code run?
On your own machines. You attach self-hosted workers, and agent runs execute there — your code and repositories never leave your infrastructure.
Which agents and models are supported?
IssueFlow ships bundled integrations for Claude Code, Cursor Agent, Copilot CLI, OpenCode and Gemini CLI, and ships no agent of its own. Assign one per stage, set the model per stage, or give a stage a script instead.
Do I have to put a human gate on design?
No. Gates go wherever you decide — design, the pull request, deploy, several, or none. The founder gates design because that's where his judgment matters most; that's an example, not a rule.
Where does my workflow live?
In your repository, as config the portal writes for you — no hand-edited YAML. Each stage's output, such as a design spec, is published on the issue itself, so the record stays with the work.
Not ready to pick a tier?
Follow the build instead. Occasional notes on loop engineering and governed agentic delivery — and you will hear it here first when pricing or capabilities change. No spam, unsubscribe anytime.