经 AI Skill Hub 精选评估，代码审查智能工具 获评「强烈推荐」。这款Agent工作流在功能完整性、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。
代码审查智能工具 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
代码审查智能工具 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一：pip 安装（推荐）
pip install inspect
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install inspect
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/Ataraxy-Labs/inspect
cd inspect
pip install -e .
# 验证安装
python -c "import inspect; print('安装成功')"
# 命令行使用
inspect --help
# 基本用法
inspect input_file -o output_file
# Python 代码中调用
import inspect
# 示例
result = inspect.process("input")
print(result)
# inspect 配置文件示例（config.yml） app: name: "inspect" debug: false log_level: "INFO" # 运行时指定配置文件 inspect --config config.yml # 或通过环境变量配置 export INSPECT_API_KEY="your-key" export INSPECT_OUTPUT_DIR="./output"
Part of the Ataraxy Labs stack — agent-native infrastructure for software development. See also: sem (semantic version control) · weave (entity-level merge driver) · opensessions (tmux sidebar for coding agents). Read the manifesto: https://ataraxy-labs.com/#thesis · Essays: https://ataraxy-labs.com/blogs · LLMs: https://ataraxy-labs.com/llms.txt
<p align="center"> <img src="assets/logo.svg" alt="inspect" width="80" /> </p>
<p align="center"> <strong>inspect</strong> </p>
<p align="center"> <strong>Entity-level code review for Git.</strong><br> Triage PRs by structural risk, not line count. </p>
inspect is a code review tool that works at the entity level instead of files or lines. It parses your diff with tree-sitter, classifies each changed entity (text-only, syntax, functional), scores it by risk using the cross-file dependency graph, and groups independent changes so tangled commits can be reviewed as separate units.
Every code review tool today shows you files and lines. inspect shows you which functions matter. A renamed variable, a reformatted function, and a deleted public API method all look the same in a line diff. inspect scores the API deletion as critical (high blast radius, many dependents) and the rename as low risk. Review the critical stuff first, skip the noise.
On the Greptile benchmark (141 findings across 52 PRs), inspect achieved 95.0% recall vs Greptile's 91.5% and CodeRabbit's 56.0%. On the Martian benchmark (137 findings, 50 PRs), inspect scored 46.2% F1, beating Augment Code (45.8%) for #1 on their leaderboard.
Agents and CI pipelines consume inspect through JSON output or the built-in MCP server (6 tools). Developers use the CLI to triage locally before pushing.
cargo install --git https://github.com/Ataraxy-Labs/inspect inspect-cliOr build from source:
git clone https://github.com/Ataraxy-Labs/inspect
cd inspect && cargo build --releasecargo build -p inspect-mcp
inspect review HEAD~1 --provider ollama --model llama3
inspect review HEAD~1 --api-base http://localhost:8000/v1 --model my-model ```
| Provider | API key env var | Default base URL |
|---|---|---|
anthropic | ANTHROPIC_API_KEY | api.anthropic.com |
openai | OPENAI_API_KEY | api.openai.com/v1 |
ollama | none | localhost:11434/v1 |
--api-base implies the OpenAI-compatible client, so you don't need --provider with it. --provider ollama implies localhost:11434, so you don't need --api-base with it.
For teams that don't want to manage LLM infrastructure, we run a hosted review service at inspect.ataraxy-labs.com. It goes beyond what inspect review does locally.
What the hosted API does differently:
```bash
创新的实体级代码审查方案，结合代码图和AI代理技术，有效提升PR审查效率。Stars虽中等但方向前沿，适合追求自动化审查的开发团队。
该工具使用 NOASSERTION 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
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。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评：代码审查智能工具 的核心功能完整，质量优秀。对于自动化工程师和运维人员来说，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 | inspect |
| 原始描述 | 开源AI工作流：Entity-level code review. Triages pull requests by structural risk using cross-f。⭐145 · Python |
| Topics | 代码审查AI工作流代码智能PR分类结构分析 |
| GitHub | https://github.com/Ataraxy-Labs/inspect |
| License | NOASSERTION |
| 语言 | Python |
收录时间：2026-05-22 · 更新时间：2026-05-22 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端