For indie hackers and solo SaaS builders

Nobody reviews your code.Now something does.

Every pull request reviewed by the AI account you already have, or by free models.

Run it freegit clone https://github.com/BridgLabs/opencodereview && cd opencodereview && docker compose up --build

5 minutes with Docker · No account, no card · Free for individuals and small companies

localhost:1421/platform/reviews
The OpenCodeReview Reviews page: pull requests grouped by status, and a finished review with two findings

The real app, filled with demo data.

Works with

Shipping solo

When you're the only developer, nobody catches your mistakes.

Reviewing your own code

  • You approve your own pull requests, or skip them and push to main.
  • You read code you wrote an hour ago and see what you meant, not what you wrote.
  • The bug reaches you as a support email from a paying customer.

Paying for a review bot

  • Another monthly subscription, on a product that may not pay for itself yet.
  • Priced and built for teams of fifty, not for one person and a few repos.
  • You pay for AI again, on top of the AI plan you already have.

It's for you if…

  1. You build a SaaS, an app or a side project alone, or with one cofounder, and there is no one to review your code.
  2. You already pay for Claude, ChatGPT or Gemini, or pay for nothing yet, and don't want a second AI bill just for reviews.
  3. You've shipped a bug a second pair of eyes would have caught, and you'd rather hear it from a bot than from a customer.
Minutesto a first review on every new pull request
$0extra, on top of the AI plan you already have
No middlemanonly you and your AI provider see the code

Before and after

Same pull request. Different morning.

Without
Add yearly plans to checkout#58
You opened this pull request11:48 PM
No reviewers · you merged it yourself11:49 PM
Stripe retries a webhook and charges a customer twice3:10 AM
Refund request in your inbox8:02 AM
With OpenCodeReview
Add yearly plans to checkout#58
You opened this pull request11:48 PM
OpenCodeReview reviewed it with the whole repo as context11:52 PM
youcommented via OpenCodeReview · 4 min after opening

⚠️ OpenCodeReview found 2 issues

Reviewed 9e1c2f7. Each issue below has the details and a suggested fix.

IssueWhere
⚠️Webhook is not idempotent: a Stripe retry charges the customer twicewebhook.ts:42
⚠️Yearly price id is read from process.env without a fallbackplans.ts:12

Reviewed by OpenCodeReview, source-available AI code review with the AI account you already have.

Fixed in 1 commit · merged at 12:06 AM · you went to sleep

Illustrated example.

From clone to your first review.

Four steps, about five minutes. You never write a config file.

$ git clone …/opencodereview
$ docker compose up --build
✓ open localhost:1421

1. Plug it in

One Docker command starts everything. Open localhost:1421 and onboarding takes over.

GitHub
you✓
you/saas-app
you/landing

2. Show it your repos

Sign in with GitHub and pick the repositories. They're cloned and indexed in the background.

Your AI plan
Claude✓
ChatGPT
Gemini

3. Bring your own brain

Sign in to Claude, ChatGPT or Gemini in the browser, or use OpenCode's free models. Every CLI ships inside the container.

#58 reviewed

4. Watch the first review

Pick an open pull request. From then on, every new one is reviewed as soon as you open it.

A reviewer that read the whole repo

Every review starts from an index of your codebase: who calls the changed code, which tests cover it, and the rules you've written down. Findings come with the file, the line and the fix, not a wall of nitpicks.

Everything a review needs. Nothing you rent.

Your AI, your call

Review with Claude Code, Codex, Gemini or OpenCode, whichever you have. Pick which account the next reviews use.

Reviews run on
Claude MaxAnthropic✓
ChatGPT PlusOpenAI
GeminiGoogle
OpenCode GoOpenCode

Never stalls at a limit

Building with Claude all day? Add a second account. When one reaches its usage limit, the review moves to the next and comes back after the reset.

Settings, Accounts: Claude Max marked Next review with usage meters, and a ChatGPT Pro account

Knows your codebase

A local index of symbols and imports. Each review gets the callers and tests of the change, and nothing else.

webhook.ts checkout.ts plans.ts webhook.test.ts emails.ts

Your rules, as skills

Tell reviews what matters to you in plain Markdown, like "every Stripe handler must be idempotent". Each repository can have its own skill, and every edit is versioned.

you/saas-appcustom skill · v4
you/mobilecustom skill · v2
you/landingdefault skill

Lands where you review

A summary on the pull request, and each issue inline on the line it is about.

youcommented via OpenCodeReview · 4 min after opening

⚠️ OpenCodeReview found 2 issues

IssueWhere
⚠️Webhook is not idempotent: a Stripe retry charges the customer twicewebhook.ts:42
⚠️Yearly price id is read from process.env without a fallbackplans.ts:12

Reviewed by OpenCodeReview, source-available AI code review with the AI account you already have.

Stays on your machine

Your repositories, index, sign-ins and review history live on your laptop or your own server. We have no servers to send them to.

On this machine
Repositories and index
AI sign-ins and API keys
Review history

What it costs

The bill for code review: nothing.

No seats, no tiers, no locked features. Put in your numbers and see what a hosted reviewer would add to your monthly bills.

Per-seat tool, per year$288
OpenCodeReview, per year$0

Same reviews. Different deal.

Hosted review tools are built for engineering teams: billed per developer, running your code through their cloud. OpenCodeReview runs on the AI plan you already have.

OpenCodeReviewSelf-hosted · source-availableCodeRabbitHosted serviceGreptileHosted service
Price✓Free for individuals and small companies, on your AI plan✕Per developer, monthly✕Per developer, monthly
Where your code runs✓Your machine; only your AI provider sees the diff✕Their cloud~Their cloud, or self-hosted on enterprise
Models✓Claude Code, Codex, Gemini or OpenCode~Vendor's choice~Vendor's choice
Usage limits✓Fails over across your accounts~Your plan's limits~Your plan's limits
Whole-repo context✓Local index✓Yes✓Yes
Source code available✓Yes✕No✕No

Based on each product's public website. Plans change, so check their pricing pages for current details.

For teams

Your side project became a company?

OpenCodeReview is free for individuals and companies under 100 people and $1M in revenue. Past that, your company needs a commercial license, so talk to us.

  • Setup with youWe install it on your infrastructure, connect your repositories and tune the review skills to your codebase.
  • Commercial licenseFor companies with 100 or more people or $1M or more in revenue.
  • SupportA direct line to the maintainer, with priority fixes.
  • Shape the roadmapTell us what your team needs next, such as SSO, organization-wide skills or review reports.
Opens your email app with the message ready to send.
I work alone. Isn't code review for teams?

That is exactly why you need it. On a team, someone else reads your diff before it ships. Alone, nobody does. OpenCodeReview is that someone, for every pull request, in a few minutes.

I push straight to main. Does it still work?

It reviews pull requests. Open a branch and a pull request for each change, even if you merge it yourself ten minutes later. The review lands before you merge.

Is OpenCodeReview really free?

For individuals and companies under 100 people and $1M in yearly revenue, yes, including commercial use. Larger companies need a commercial license. Reviews run on your own Claude, ChatGPT or Gemini account, or on OpenCode's free models, so the only cost is what you already pay your AI provider.

Which plans work?

Claude Pro, Max or Team through Claude Code, ChatGPT plans that include Codex, a Google account through the Gemini CLI, and OpenCode's free models or an OpenCode Go key. Local models are not supported. You can connect several accounts of each kind.

What happens when my plan hits its limit?

The review continues on your next account in order. The limited account rests and is used again after its window resets. Claude and ChatGPT accounts show how much usage they have left; API keys are billed by their provider.

Where does my code go?

It stays on the machine that runs OpenCodeReview. Reviews call your AI provider with your own sign-in or key, the same way its CLI does when you use it yourself.

How is it different from CodeRabbit or Greptile?

They are hosted services billed per developer. OpenCodeReview is self-hosted with its source available, and it reviews with the AI plan you already pay for.

Does my laptop need to stay on?

Reviews run while OpenCodeReview is running. For reviews around the clock, run it on any always-on machine with Docker, such as a small VPS or a home server.

What do I need to run it?

Docker, a GitHub account with access to your repositories, and a Claude, ChatGPT or Gemini account. Without one, OpenCode's free models work. The Claude Code, Codex, Gemini and OpenCode CLIs ship inside the container.

Does it work with GitHub Enterprise?

Yes. Set OCR_GH_HOST to your GitHub host before starting it.

Stop being your own only reviewer.

Clone it, connect GitHub and your AI account, and get your next pull request reviewed in five minutes.

5 minutes with Docker · No account, no card · Free for individuals and small companies