agentgg - Open source agentic SAST. The engine behind hundre

项目说明

<p align="center">
<img src=" alt="agentgg" width="240" />
</p>

agentgg

Agentic SAST. White box. CI ready.

agentgg is an agentic SAST scanner. Its agents read your code and reason about it — they follow imports, check the call graph, and confirm a finding before they report it, instead of pattern-matching the way traditional SAST does. Run it over a whole repository, or over a git diff for pull request review. Every scan opens with a fast recon pass that briefs the agents on what the project is, and an interrupted scan resumes on re-run.

Documentation · agentgg.dev · Platform · Agents catalog · Report a bug · Report a security issue

Help us grow and star us on GitHub! ⭐️

> agentgg is in beta. Things will move and edges will be rough. Bug reports and feedback are very welcome. Open an issue.

<p align="center">
<img src=" alt="agentgg UI showing scan findings" width="780" />
</p>

Install

> Don't want to run it locally? app.agentgg.dev runs the same scanner as a hosted service: upload a repo, no install, no provider key of your own.

Requires Node.js 20+. You also need an account with one model provider — Anthropic, OpenAI, AWS Bedrock, Google AI, OpenRouter, or a local Ollama. See Pro for setup, and CONTRIBUTING.md to build from source.

Quick start

A scan writes summary.md and one markdown file per finding into ./out/, plus a state/ directory that makes resume, status, and re work. Re-run with the same -o and unchanged files are skipped; a different -o starts fresh.

Walkthrough: Quickstart.

Documentation

Browse the full documentation at docs.agentgg.dev.

Agents

An agent is one markdown file: YAML frontmatter that declares where to look and an optional precondition that decides whether the agent is worth running on this repo, plus a markdown body that is the prompt. An agent that declares neither extensions nor filePatterns in its where has no file scope: it gets no pre-selected files and searches the whole repository with its own tools instead. The catalog auto-downloads on first scan from agentgg-de, and agentgg create turns a past incident report into a reusable agent.

Write your own: Agent anatomy · Targeting · Create from reports

Contributing

Bug reports, agents, and pull requests are all welcome. See CONTRIBUTING.md for the de, CODE_OF_CONDUCT.md for community expectations, and SECURITY.md to report a pri.

License

agentgg is licensed under the Apache License, 2.0. See LICENSE for the full text and NOTICE for attribution.

项目信息

开发语言：TypeScript

Star 数：419

技术要点

该项目属于安全软件方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own model.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。