AI Agent Analysis

vercel-labs/deepsec

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

stars

7.7k

Language

TypeScript

Source and compliance noteLast synced: Aug 16, 2026

Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.

Original GitHub source Methodology Editorial Policy

Overview

Deepsec is an agent-powered vulnerability scanner that runs on your own infrastructure, designed to find hard-to-detect security issues in large-scale codebases by using advanced AI models at maximum thinking levels.

Installation

Run `npx deepsec init` in your repo root, then `cd .deepsec && pnpm install`.

Problem solved

Deepsec solves the problem of finding subtle, long-lurking vulnerabilities that traditional static analysis tools miss, by leveraging coding agents that deeply understand code context. It is optimized for large monorepos where manual review is impractical, and can resume interrupted scans.

What you can build

Developers can build automated security audits for their entire codebase, integrate vulnerability scanning into CI/CD pipelines via `process --diff`, and create custom matchers for project-specific patterns. Real-world use cases include finding auth bypasses, injection flaws, and logic errors in web apps, with the ability to scale across distributed workers for massive repos.

Community sentiment

Positive

No community feedback yet.

Concerns

No concerns documented yet.

Bottom line

Deepsec is for teams with large, security-critical codebases who can afford high compute costs (thousands of dollars) and want deep, agent-driven vulnerability discovery. It should be avoided by small projects or those with limited budgets. The key trade-off is thoroughness vs. cost and runtime.

Analyzed by Git-Stars - 7/21/2026