# lintsinghua/DeepAudit

DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。​让安全不再昂贵，让审计不再复杂。

Repository: https://github.com/lintsinghua/DeepAudit
Canonical: https://ross.abutalabs.com/products/deepaudit
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: ai, bug-detection, code-audit, code-quality, code-review, developer-tools, devsecops, google-gemini, llm, react, sast, security-scanner, supabase, typescript, vite, vulnerability-scanner, xai
Last push: 2026-08-17T06:08:15+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 67, longevity 24
- inputs: {"age_days": 348, "days_push": 16, "days_rel": 221, "gap_med": 1, "n_releases_24m": 24}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6905, forks 846 (observed 2026-08-28T04:09:51.195112+00:00)

## What it is
DeepAudit is an open-source multi-agent AI system for automated code vulnerability discovery and security auditing, with a React frontend and FastAPI backend. It coordinates collaborating AI agents to audit codebases, verifies findings with automated sandbox PoC exploits, and generates exportable reports, supporting private deployment via Ollama.

## Use cases
- find security vulnerabilities in my codebase with AI
- run automated static analysis security testing on a repository
- verify suspected vulnerabilities with sandboxed PoC exploits
- self-host a private code audit tool with local LLMs via Ollama
- generate professional security audit reports as PDF or Markdown
- audit GitHub/GitLab projects from a web dashboard

## When to choose
- you want LLM-driven multi-agent security auditing of source code
- you need automated PoC validation to reduce false positives
- you require private/on-premise deployment with local models
- you want one-click reports and a web UI for managing audit projects

## When to avoid
- you need a lightweight traditional SAST scanner without LLM costs
- you require guaranteed soundness or compliance-certified scanning
- your codebase cannot be shared with an LLM and you cannot run local models
- you need real-time CI gating rather than interactive audit sessions

## Facets
- artifact type: application
- maturity: active
- function: vulnerability-scanning, security, agent-framework, llm-inference, code-review, developer-tools
- domain: security, developer-tools, artificial-intelligence, large-language-models
- platform: python, self-hosted, cross-platform
- tags: sast, code-audit, multi-agent, poc-verification, ollama, devsecops, vulnerability-detection, report-generation, ai-agents, docker, web-server

## Member repositories
- lintsinghua/DeepAudit (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.195112+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:41:28.761015+00:00, confidence not recorded.
  - readme: https://github.com/lintsinghua/DeepAudit (fetched 2026-08-28T04:09:51.195112+00:00, sha 036499485b33)
- Data as of 2026-08-30T08:39:29.467469+00:00.