Refraction uses AI to refactor code, generate documentation, and create unit tests from code samples.
OpenCodeReview
OpenCodeReview combines deterministic checks and language model agents for code review with line-level comments.
About OpenCodeReview
OpenCodeReview is an open source command-line tool that reviews Git diffs with a configurable language model agent. It pairs deterministic file selection and pipelines with agent tool use to generate structured comments with line-level precision.
The agent can read full file contents, search the codebase and inspect related changed files for context. An ocr scan mode reviews entire files when there is no meaningful diff, and the tool includes built-in checks for issues such as NPE, thread-safety, XSS and SQL injection. Use requires configuring an OpenAI or Anthropic compatible model endpoint.
Key features
- Reviews Git diffs through configurable LLM agent with tool use
- Generates structured review comments with line-level precision
- Reads full file contents and searches codebase for context
- Scans entire files without meaningful diffs via ocr scan
- Includes built-in rules for NPE, thread-safety, XSS, SQL injection
- Works with OpenAI and Anthropic compatible model endpoints
Best for: Developers and teams who review Git changes and want line-level, context-aware review comments.
Good for
- Open source with configurable OpenAI and Anthropic compatible endpoints
- Agent uses full file contents and codebase search beyond the diff
- Includes built-in multi-language rules for NPE, thread-safety, XSS and SQL injection
Watch out for
- Reported recall is lower than general-purpose agents, trading coverage for precision
- Requires configuring an external model endpoint before use
OpenCodeReview at a glance
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
OpenCodeReview alternatives
Tools and sites you could use instead, ranked by how closely they match.
LangWatch provides evaluations for language models and tests for AI agent applications.
Open source
16 alternatives
This repository contains code for PR-Agent, an open source tool for reviewing pull requests.
Open source
19 alternatives
ReviewCerberus analyzes Git branch differences and generates code review reports using AWS Bedrock or Anthropic API.
Open source
15 alternatives
PR-Agent provides automated review of software pull requests in this open source repository.
Open source
17 alternatives
Blinky provides an open-source AI debugging agent integrated into Visual Studio Code.
Open source
11 alternativesPopular in AI Code Review & Testing
Well-known listings from the same topic.
Prediction Guardpredictionguard.comGreptilegreptile.comGitAutogitauto.aipromptfoopromptfoo.devKatalonkatalon.comQodoqodo.ai
OpenCodeReview FAQ
Which models can it use?
It uses a configurable endpoint that is OpenAI and Anthropic compatible.
Can it review code without a Git diff?
Yes. The ocr scan mode reviews entire files for auditing codebases or directories with no meaningful diff.
What does the agent examine during a diff review?
It reads changed files, can read full file contents, search the codebase, and inspect other changed files for context.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.