# vercel-labs/deepsec

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

Repository: https://github.com/vercel-labs/deepsec
Canonical: https://ross.abutalabs.com/products/deepsec
Homepage: https://deepsec.sh/
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T21:31:05+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 8
- inputs: {"age_days": 125, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7828, forks 469 (observed 2026-08-28T04:10:05.291816+00:00)

## What it is
Deepsec is an open-source, agent-powered vulnerability scanner that runs AI coding agents over your entire existing codebase to find hard-to-detect security issues. It is distributed as an npm CLI, runs in your own infrastructure with VM fanout for large repos, and supports resumable scans, cost caps, and CI gating.

## Use cases
- scan my whole repository for security vulnerabilities with AI
- find hidden security bugs in a large legacy codebase
- run an AI security review on all existing code, not just pull requests
- self-host a vulnerability scanner using my own OpenAI or Anthropic API key
- gate pull requests on AI security review in CI
- audit a codebase for SQL injection, XSS, SSRF, and auth issues

## When to choose
- you want a deep, whole-repository security review rather than per-PR linting
- you can tolerate high LLM costs (potentially thousands of dollars) in exchange for thorough findings
- you need the scan to run in your own infrastructure with agent sandboxing
- you want resumable, interruptible scans with cost and duration caps

## When to avoid
- you need fast, free, deterministic static analysis on every commit
- your budget cannot absorb large LLM inference costs
- you need compliance-certified or signature-based SAST tooling rather than AI-driven review
- your codebase is small enough that a manual or lightweight scanner review suffices

## Facets
- artifact type: cli-tool
- maturity: active
- function: security, vulnerability-scanning, agent-framework, cli, developer-tools
- domain: security, developer-tools, artificial-intelligence, large-language-models
- platform: cli, cross-platform
- tags: ai-security-review, vulnerability-scanner, code-review, llm-agent, self-hosted-security, sast, codebase-audit, nodejs, docker

## Member repositories
- vercel-labs/deepsec (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:05.291816+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 2026-08-29T17:34:08.360562+00:00, confidence not recorded.
  - readme: https://github.com/vercel-labs/deepsec (fetched 2026-08-28T04:10:05.291816+00:00, sha c49c02bc7444)
  - homepage: https://deepsec.sh/ (fetched 2026-08-29T08:31:02.500403+00:00, sha b27ee40079bd)
  - site_page: https://vercel.com/docs (fetched 2026-08-29T08:31:02.509128+00:00, sha 614e0cfe00de)
  - site_page: https://vercel.com/about (fetched 2026-08-29T08:31:02.511045+00:00, sha c78127d6b6a3)
  - site_page: https://vercel.com/docs/frameworks/full-stack/nuxt (fetched 2026-08-29T08:31:02.516040+00:00, sha 3e48525fbcdd)
  - site_page: https://vercel.com/docs/frameworks/full-stack/sveltekit (fetched 2026-08-29T08:31:02.518007+00:00, sha fec9e6e22eeb)
  - site_page: https://vercel.com/docs/frameworks/backend/nitro (fetched 2026-08-29T08:31:02.520100+00:00, sha f304c099ad65)
  - site_page: https://vercel.com/docs/frameworks/full-stack/tanstack-start (fetched 2026-08-29T08:31:02.521822+00:00, sha fb46d1029e2d)
  - registry_npm: https://registry.npmjs.org/deepsec (fetched 2026-08-29T08:31:02.523616+00:00, sha 68bb6eb66d19)
  - site_page: https://vercel.com/changelog (fetched 2026-08-29T08:31:02.512649+00:00, sha 002ff21b7089)
- Data as of 2026-08-30T08:39:29.467469+00:00.