Deepsec

github.com
July 19, 2026
4 min read
44/100
Summary
Deepsec is an agent-powered vulnerability scanner that performs on-demand reviews of large-scale code repositories to identify hard-to-find issues. It utilizes advanced models at maximum thinking levels, which can result in high scanning costs for extensive codebases.
Key Takeaways
- Deepsec is an agent-powered vulnerability scanner designed for on-demand review of large-scale code repositories.
- The tool can surface hard-to-find vulnerabilities and is optimized to run scans in parallel across worker machines.
- Deepsec requires a subscription to AI services like Claude or Codex for full repository scans, with Vercel AI Gateway recommended for real scans.
- The scanning process can be resumed if interrupted, allowing it to pick up where it left off without re-analyzing previously scanned files.
Coverage & discussions
Hacker News · github.com
Community discussions
Community Sentiment
Positives
- The Swival Audit feature is impressively effective, even with smaller, open models, indicating that you don't always need the biggest tools for solid results.
Concerns
- Subscriptions for tools like Claude Pro and ChatGPT Plus seem limiting for comprehensive repo scans, suggesting that the pricing models aren't aligned with deep analysis needs.
Related Articles

Anthropic's open-source framework for AI-powered vulnerability discovery
Jun 4, 2026

Get Shit Done: A Meta-Prompting, Context Engineering and Spec-Driven Dev System
Mar 17, 2026

Claude Code – Everything You Can Configure That the Docs Don't Tell You
May 29, 2026

Understand Anything
May 1, 2026

Open-source memory for coding agents, synced over SSH
Jul 15, 2026