ThrillhouseBot

“Everything’s coming up Thrillhouse!”

A self-hosted, GraalVM-native PR review bot, built as a GitHub App with Quarkus. It reviews pull requests using any OpenAI-compatible chat API, so the review is language-agnostic and you can pick the provider that suits you — including a local Ollama model, so no code has to leave your network.

Features

• Reviews diffs for correctness, security, regressions, stale comments and code quality, and tags every finding critical, high, medium or low
• Reviews large pull requests whole: the diff is split into token-budgeted batches reviewed in parallel, and any file that does not fit is named
• Inline suggestions you can apply with one click
• A second pass re-checks each finding against the diff before it is posted
• Follow-up reviews track whether earlier findings were fixed, declined or are still open, and re-check a maintainer's decline against the code
• One summary comment per pull request, edited in place every round, with a risk breakdown, a changed-files walkthrough and every finding still open
• Comment commands (/review, /summary, /describe, /changelog, /add-docs, /improve, /generate-tests, /resolve, /pause, /resume, /help, and with learnings on /learnings, /remember, /forget) and conversational replies to @thrillhousebot
• Auto-review triggers: skip drafts, gate on labels, filter by base branch, and optionally space out reviews of one PR (AUTO_REVIEW_MIN_INTERVAL)
• Maintainer 👍/👎 reactions and "not useful" replies are recorded as finding feedback
• Optional review context, each off by default: the issues a PR links and their acceptance criteria, the CI checks that already failed on the head commit, patch coverage from your own coverage report, and review learnings (maintainer declines and /remember conventions from earlier reviews of the same repository)
• Optional deterministic scan of added lines for leaked credentials and risky Terraform, Kubernetes, CloudFormation and Dockerfile settings, with no model call and every matched secret redacted
• Optional per-call review dimension routing, which sends each call only the review rules its files need
• Optional outgoing notification when a review completes or fails: JSON, Slack or Discord, HMAC-signed, metadata only unless you opt in
• Per-repository instructions in .github/thrillhousebot.md (falling back to Copilot, Claude and Agents files) and per-repository ignore globs and path-scoped rules in .github/thrillhousebot.yml
• Optional reasoning-effort setting and per-model generation and budget caps
• Live dashboard (Next.js) with a WebSocket activity feed, cost charts and token tracking
• OpenTelemetry traces, token histograms, cost counters and latency metrics

Where to go next

• Getting started — create the GitHub App with the hosted installer and run the bot with Docker Compose.
• Commands — drive the bot from a PR: /review, /describe, /changelog, /add-docs, /improve, /generate-tests, and more.
• Configuration — every environment variable, with defaults.
• AI providers — point the bot at the OpenAI-compatible endpoint of your choice.
• Architecture — how a review flows through the system.
• Finding feedback — maintainer 👍/👎 capture, and how it differs from review learnings.
• How it compares — an honest look at where ThrillhouseBot sits next to other AI code-review tools.
• Contributing — development setup and the CI bar.

Dashboard

The built-in dashboard (Next.js, served by the bot itself) shows summary cards, a live activity feed that streams the model’s output as a review runs, cost charts by model, token breakdowns, and a paginated session history:

Community and license

Questions and setup help belong in GitHub Discussions; bugs and feature requests in Issues.

Licensed under the Apache License 2.0 (SPDX: Apache-2.0).