01
Issue
A scoped issue carries intent, context, and acceptance criteria.
Closed beta · invite-only
One developer, the output of a thousand engineers.
An AI automation platform that puts a fleet of coding agents to work on your own hardware, with your own LLM keys. Triaging issues, carrying them to reviewed, CI-green pull requests, and standing oncall 24/7. Every action is audited; the bot always discloses.
Agent 01
Upgrade zod across services
- Read repository context
- Proposed implementation plan
- Running checks
Agent 02
Fix auth redirect loop
- Read repository context
- Proposed implementation plan
- Writing tests
Agent 03
Refresh the quickstart
- Read repository context
- Proposed implementation plan
- Opening pull request
Audited end to endGitHub-native workflowExisting checks stay in controlCost visible per task
One system, end to end
From issue to merged PR, without the babysitting.
Three steps, fully receipted. The loop your team can inspect at every stage.
02
Pull request
The dev plans, patches, tests, and opens a reviewable PR.
03
Receipt
Every tool call, check, decision, token, and dollar is recorded.
Control plane
Run a fleet without losing the thread.
One view for queues, budgets, blocked work, review status, and the evidence behind every active maintainer.
Explore how it worksPull request #731
Handle expired workspace tokens
+ if (token.expiresAt < Date.now()) {
+ await rotateWorkspaceToken(token)
+ }8 files changed · +94 −21Policy passed
Observe every handoff
Autonomy your team can actually inspect.
Step through the run to see what your team receives at every stage, not only the final diff.
Merges only happen past your gates: CI green, review, branch protections.
- Reads the issue and maps the repo01
- Proposes a scoped plan02
- Estimates cost before touching code03
- Works in a branch on your keys01
- Runs your checks continuously02
- Documents every decision03
- Opens a focused pull request01
- Attaches the execution receipt02
- Auto-merges only past your gates03
One flat price. No quotas. Your hardware.
Every competitor rations usage. We don't. Your token bill is your only variable cost.
Pricing
$100 – $1000 / ai-dev / mo$20 – $200 / mo + quota caps
Flat per-seat pricing. No file-level add-ons, no per-minute metering.
Quotas
Zero usage limitsTask / file / minute caps
Your LLM token bill is your only variable cost.
Hardware
3 CI boxes per ai-dev, on your VPSTheir infra (or CI-only BYOC)
Run the agents on hardware you control. No data leaves your network.
BYOK
Any OpenAI-compatible keyTokens billed by the vendor
Bring your own key, or ours. Never locked in.
Fleet + Review + CI
All three in one AppCoding only / Review only / CI only
Triage, fix, review, ship. One platform, no per-product handoffs.
See the full comparisonEach rival has its own breakdown: pricing, quotas, hardware, BYOK, fleet.Open the side-by-side
Prices verified July 2026 from public pricing pages.
Assign an issue. Watch the plan. Review the evidence. Merge when it earns your approval.
Less context switching
More finished maintenance
No new merge shortcuts
Questions
Frequently asked questions
Does the bot pretend to be human?
Never. Every comment it posts discloses that it's an automated agent. Non-disclosure is a bug, not a setting.
Whose API keys does it use?
Yours. BYOK is the only mode, your own Anthropic, OpenAI, Gemini, Kimi, GLM, MiniMax, DeepSeek, xAI, Groq or OpenRouter key, or any OpenAI-compatible endpoint. We never resell tokens.
Does it write the code?
No. It's a thin orchestrator: it triages and coordinates, then hands coding to your agent (Copilot, Claude Code, or OpenHands).
Can I see what it did?
Yes. Every tool call and decision is logged. If it isn't logged, it didn't happen.
What about CodeRabbit or Dependabot?
It detects other bots and defers: no bot-on-bot loops. It waits for their reviews to settle before acting.
Put a fleet of AI developers to work
Bring your own keys and your own boxes, drop a .maintainer.yml, and let the loops run. Audited end to end. Access is invite-only.