经 AI Skill Hub 精选评估,本地代码审查 获评「强烈推荐」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
本地代码审查 是一款基于 Go 开发的开源工具,专注于 ai、cli、code-review 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
本地代码审查 是一款基于 Go 开发的开源工具,专注于 ai、cli、code-review 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:go install(推荐) go install github.com/mshykov/local-review@latest # 方式二:从源码编译 git clone https://github.com/mshykov/local-review cd local-review go build -o local-review . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/mshykov/local-review/releases
# 查看帮助 local-review --help # 基本运行 local-review [options] <input> # 详细使用说明请查阅文档 # https://github.com/mshykov/local-review
# local-review 配置说明 # 查看配置选项 local-review --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export LOCAL_REVIEW_CONFIG="/path/to/config.yml"
<p align="center"> <img src="docs/logo.svg" alt="local-review logo" width="200"/> </p>
<p align="center"> <strong>Local, BYOK code review for any language.</strong><br> Runs against a git diff, hands it to whichever LLM you point it at, prints findings.<br> No SaaS, no telemetry, no signup. </p>
<p align="center"> <a href="https://github.com/mshykov/local-review/releases"><img src="https://img.shields.io/github/v/release/mshykov/local-review?style=flat-square" alt="Release"></a> <a href="https://github.com/mshykov/local-review/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg?style=flat-square" alt="License"></a> <a href="https://github.com/mshykov/local-review/stargazers"><img src="https://img.shields.io/github/stars/mshykov/local-review?style=flat-square" alt="Stars"></a> </p>
<p align="center"> <a href="#why-local-review">Why</a> • <a href="#how-good-is-it">How good is it?</a> • <a href="#get-started">Get started</a> • <a href="CHECKLIST.md">Checklist</a> • <a href="#customise-for-your-team">Customise</a> • <a href="https://mshykov.github.io/local-review">Website</a> </p>
---
llms: claude: model: claude-opus-4-7
gemini: model: gemini-2.0-flash api_key_env: GEMINI_API_KEY
codex: enabled: false # opt-out (still runs if --only codex is passed)
merge: preferred_llm: auto # or: claude, gemini, codex ```
See examples/.local-review-multi.yml for full schema.
prompts: prepend: | Additional house rules: - Never approve commented-out code. - Flag any new dependency in package.json or go.mod. review: min_severity: warning # nit | info | warning | major | critical
You can ship the whole pack of overrides this way — see [Customise for your team](#customise-for-your-team) below.
**4. Review your current branch** vs `main`:
sh local-review review ```
Findings print to your terminal. The tool exits non-zero on major / critical, so it slots straight into a pre-commit hook.
5. (Optional) Check how the LLMs score on a labelled benchmark. The repo ships with bench/RESULTS.md — a leaderboard (precision / recall / F1 / noise, plus uplift-over-raw-LLM and overhead-vs-raw-LLM tables) generated from a 10-case dataset spanning Go / TS / Python / Rust. Refreshed before each release; you don't need to run anything locally. See bench/README.md for methodology.
---
local-review review --only claude,gemini
local-review loads YAML from a cascade — built-in defaults → ~/.local-review.yml → ./.local-review.yml → CLI flags.
A minimal ~/.local-review.yml:
provider:
base_url: https://api.openai.com/v1
model: gpt-4o-mini
api_key_env: LOCAL_REVIEW_API_KEY
review:
min_severity: warning
max_findings: 20
See examples/.local-review.yml for the full schema with comments.
local-review review [<base>] # canonical: current branch vs <base> (default: main) local-review staged # review git diff --cached (pre-commit) local-review commit [<rev>] # review one commit (default: HEAD) local-review branch [<base>] # alias of review for muscle-memory
高质量的本地代码审查工具,支持多语言
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:本地代码审查 的核心功能完整,质量优秀。对于AI 技术爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | local-review |
| 原始描述 | 开源AI工具:Local, BYOK code review for any language. No SaaS, no telemetry.。⭐13 · Go |
| Topics | aiclicode-reviewgolang |
| GitHub | https://github.com/mshykov/local-review |
| License | MIT |
| 语言 | Go |
收录时间:2026-05-25 · 更新时间:2026-05-26 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。