GitHub App · Managed OpenAI · Runs included

AI agents that find
real bugs in your PRs

A fleet of AI agents reviews every pull request, debates each finding, and only reports bugs that survive consensus verification.

pr-hunt output
$ pr-hunt --pr 847 --fleet-size 5
[14s] Spawned bug_finder_early agent: agent-a1b2
[14s] Spawned bug_finder_early agent: agent-c3d4
[38s] Bug submitted: off-by-one in pagination
[52s] Bug submitted: unchecked null in auth flow
[71s] Verification: 5/5 confirmed · 0 refuted
CONFIRMED [high] unchecked null in auth flow
File: src/middleware/auth.ts:42
CONFIRMED [medium] off-by-one in pagination
File: src/api/list.ts:118
✓ 2 bugs confirmed, 0 false positives

How it works

Three steps. Zero infrastructure.

01

Subscribe

Choose Starter ($39) or Pro ($99). Runs are included each billing period.

02

Connect GitHub + Install App

Connect your GitHub login in the dashboard, then install the PR Hunt GitHub App on the repos you want to use.

03

Trigger a run

Comment /pr-hunt run on a pull request. Only the linked GitHub login can trigger runs.

PR comment
# Comment on a pull request
/pr-hunt run

Features

Not another linter.

PR Hunt finds logic bugs, race conditions, and security issues that static analysis misses.

Multi-Agent Consensus

Multiple AI agents independently review your code. Bugs are only reported after surviving adversarial verification — 5 confirmations required, skeptical verifiers trying to disprove each finding.

Managed OpenAI

No customer API keys required. PR Hunt runs in a controlled environment and meters usage per billing period.

GitHub App Workflow

Install the GitHub App once, connect your GitHub login, and trigger runs with a PR comment.

Quota + Top-Ups

Subscriptions include a run quota. Buy extra runs instantly from the dashboard. Top-ups expire at period end.

PR Comment Reports

Confirmed bugs are posted back to your PR as a consolidated comment report. Inline comments are on the roadmap.

Hard Spend Guardrails

Fixed model, bounded outputs, and reconciliation against OpenAI costs so spend can’t run away.

Stop shipping bugs.

Starter ($39) or Pro ($99). Cancel anytime.
Runs included each billing period.

View Pricing