DeepSeek Code Review

A GitHub Action and CLI tool that runs automated code reviews using DeepSeek models, commenting directly on pull requests or reviewing local git diffs from the command line.

Visit website github.com

DeepSeek Code Review automates pull-request reviews with DeepSeek models through a GitHub Action, or reviews commits locally from the command line. As a GitHub Action, it reviews new pull requests automatically, can be skipped with a marker in the PR title or body, supports interactive conversation by mentioning the bot in a PR comment, and works across macOS, Ubuntu, and Windows runners; it also skips locked PR conversations automatically.

Locally, it streams review output, can review a remote GitHub PR or local commit changes directly from the CLI, and can write results to a Markdown file. Both modes support DeepSeek's V4 and R1 models, self-hosted DeepSeek models, and customizable model, base URL, and prompt settings, and can include or exclude specific files from review.

It is written in Nushell and MIT licensed.

More in Code quality

See all 94

Critic
critic.run
A code-change viewer, backed by Y Combinator, built for reviewing work written by coding agents, presenting a plain-language narrative of each change alongside the diff and a running conversation with the agent.
- Git
- Code quality
GitIntel
hoangsonww.github.io
An MCP server that computes git repository analytics such as hotspots, churn, temporal coupling, knowledge maps and risk scoring entirely from local commit history, for AI coding agents like Claude Code and Codex.
- MCP servers
- Code quality
Axint
axint.ai
A verification layer for AI coding agents working on Apple projects: it runs real Xcode builds and tests against the Swift an agent wrote, reconciles static analysis findings against that evidence, and returns a signed proof with the exact repairs still needed.
- Code quality
- Testing

More in Code quality

Critic

GitIntel

Axint

Cookies