Get This Tool
Themis
Pricing
- Model
- Free
Summary
Most PR review automation breaks the moment you need it to enforce your team's actual standards — not a generic checklist, but the doctrine you've built up over two years of painful incidents.
Themis is a self-hosted GitHub PR review bot that runs against your own Codex or Claude Max subscription, meaning no commercial API key and no per-review billing. It posts inline findings, a structured summary with verdict and severity-ordered sections, and answers follow-up questions directly in PR threads. Review doctrine lives in a `.themis/` directory in your repository, so the bot argues from your rules, not a vendor's defaults. The self-hosted model is the differentiator — but it also means you own the deployment, the uptime, and the debugging when the webhook stops firing.
Bottom line: Pick Themis if your team already pays for Codex or Claude Max and wants consistent review enforcement without routing code through a third-party SaaS; step away if you need a managed service with no infrastructure overhead.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Uses your existing Codex or Claude Max subscription as the inference backend, so there is no additional per-review API cost on top of what you already pay.
- Repository-scoped review doctrine via `.themis/` config, which means two teams with different standards can run against the same deployed instance without interfering with each other.
- Inline findings plus a structured summary with verdict, scoring table, and severity ordering, so reviewers get a prioritized reading list rather than a flat wall of comments.
- Answers follow-up questions inside PR threads, which means a reviewer asking 'why is this flagged?' gets a response without reopening the diff or pulling in another engineer.
- MIT license with Docker-based self-hosted deployment, so the tool lives inside your network boundary and your code never leaves your infrastructure to reach a third-party review service.
Cons
Sign in to edit- No managed hosting exists — you run the webhook receiver, the container, and the model API connection yourself. The first time a container crashes during a Friday deploy window, the review bot is silent and PRs merge without it.
- The tool has no API surface of its own, which means it cannot be triggered from CI scripts, other bots, or custom tooling outside the GitHub App webhook path. Teams that need review automation embedded in a broader pipeline hit a dead end and build a wrapper or switch to a tool with a programmable interface.
- Requires an active Codex or Claude Max subscription to function — teams without either must obtain one before the bot does anything at all, making the 'free' framing conditional on existing spend.
- With 7 stars and 11 open issues against 0 pull requests at the time of scrape, the project shows limited external contribution and community momentum. Teams evaluating long-term maintenance risk will not find a large contributor base to absorb upstream issues.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Docker
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-15T18:37:32.735Z
Best For
Who it's for
- Teams wanting self-hosted PR review automation
- Users with existing Codex or Claude Max subscriptions
- Repositories requiring consistent, configurable code review
What it does well
- Automated code review of GitHub pull requests
- Inline feedback and structured summaries on PRs
- Answering reviewer questions in PR threads
- Custom review doctrine per repository
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Themis free?
- Yes — Themis is fully free to use. There is no paid tier.
- Is Themis open source?
- Yes. Themis is open source.
- Can I self-host Themis?
- Yes. Themis supports self-hosting on your own infrastructure.
- What platforms does Themis support?
- Themis is available on: Docker.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Generic linters catch style. They do not catch the architectural decisions your team has learned the hard way. Themis is a self-hosted GitHub App that reviews pull requests by running an autonomous multi-step workflow: a GitHub App webhook delivers PR and comment events, the agent reads the diff, applies your repository’s review doctrine, and posts inline findings plus a structured summary covering verdict, a scoring table, and severity-ordered sections. It also answers reviewer questions inside PR conversation threads, closing the loop without requiring a human to re-read the diff from scratch.
The sharpest edge here is doctrine portability. Review rules live in a `.themis/` directory at the root of your repository — versioned, diffable, and scoped per repo. Different teams on different repos can run different standards through the same deployed instance. This sidesteps the common failure mode where a shared review tool applies one organization-wide config that satisfies nobody.
Themis fits teams that already hold Codex or Claude Max subscriptions and want to route PR review through those credentials rather than pay a separate SaaS vendor. It is MIT-licensed and ships a Dockerfile plus docker-compose, so the deployment path is defined. The wall appears when you need managed uptime: webhook delivery, container health, and model API availability all fall on whoever owns the deployment. Teams without internal infrastructure ownership will spend more time maintaining the bot than writing the doctrine it enforces.
The tool exposes no API of its own and has no hosted tier. Integration is entirely through the GitHub App webhook mechanism. The `.themis/` configuration directory is the primary interface for customization — the docs describe this as the source of review doctrine, though the depth and syntax of that configuration layer is not fully detailed in the public README.