vigil
It enables teams to build private, AI-driven security operations centers without leaking sensitive codebases to third-party providers.
Vigil SOC: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.
- Automate the detection of security vulnerabilities within your source code
- Scan codebase logs to identify potential security threats and anomalies
- Analyze code patterns to find weaknesses before deployment
It enables teams to build private, AI-driven security operations centers without leaking sensitive codebases to third-party providers. This mitigates data exfiltration risks while automating threat detection within existing infrastructure.
Security engineering teams building localized, AI-powered SOC capabilities using private or remote large language models.
https://github.com/Vigil-SOC/vigil
By Vigil-SOC
How to Get It
claude plugins install Vigil-SOC/vigil
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Help me automate the detection of security vulnerabilities within my source code
Trust Signals Auto-scanned
Community Pulse Active
Discussed on Hacker News
- Vigil 0.5.0: threat hunting agent where a deterministic controller owns state — Hacker News · 2 pts
1 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 400 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 400 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.