Can agents use it anyway?
Yes. Arbor produces the grounded brief; an agent can use that brief to write tests or keep a patch scoped.
Back to Arbor
Pricing
Free during public beta, for public and private repos.
Use Arbor where the feedback is easiest to trust: one PR comment, one path map, one clear next check. All core features are open while the product hardens; we will give clear notice before pricing changes.
Pricing
Half the price of LLM reviewers.
None of the guessing.
Deterministic graph walks cost us almost nothing per PR — so they cost you less too. Everything is free during public beta; early installs keep a grandfathered discount when paid plans activate.
Free
$0forever
Every public repo, and a taste of private.
Unlimited walks on public repos
1 private repo, 30 walks / month
Full breakage-path PR comments
7-day run history
README risk badge
Best value
Pro
$12per dev / month
For solo devs shipping with AI agents.
Unlimited private repos & walks
Agent handoff bundles (Claude Code, Cursor, Codex)
First-test-to-write on every PR
Priority queue — faster walks
90-day history + shareable risk cards
Weekly fragile-paths digestsoon
Team
$20per dev / month
For teams that gate merges on the walk.
Everything in Pro
Merge gates — block risky PRs
Slack alerts on high-risk paths
1-year history, trends & merge radar
Risk policy as code (.arbor.yml)soon
Ownership heat on fragile pathssoon
Public beta: all tiers free today, no credit card. Pro annual is $120/year — two months free. We'll email before anything changes.
FAQ
Common questions.
How Arbor walks PRs, how agents can use the brief, and how it fits a small-team workflow.
Does Arbor run my code?
No. The worker parses and walks source structure. It does not execute your app, tests, install scripts, or runtime commands.
What if the map is incomplete?
The missing edge is named in the PR so a reviewer or agent knows where the uncertainty is.