lintsinghua/DeepAudit

Health v2 · maintenance only

Adoption not part of the score

6905 stars · 846 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

application · maturity active

vulnerability-scanning security agent-framework llm-inference code-review developer-tools security developer-tools artificial-intelligence large-language-models python self-hosted cross-platform sast code-audit multi-agent poc-verification ollama devsecops vulnerability-detection report-generation ai-agents docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lintsinghua/DeepAudit")