Suggest a Tool

Email us a link and we'll review it for inclusion.

Every listing on Neighbourhood Claw is hand-reviewed by an operator. We don't accept automated submissions yet — but we read every suggestion sent to:

mail hello@nbhdclaw.com

Include the URL, a one-line pitch, and (optionally) a category. We aim to respond within a week.

Neighbourhood Claw
Browse Tools Suggest a Tool
g0 Security tool screenshot — openclaw.ai

g0 is an open-source security control layer for AI agent systems, built by Guard0.

Added
4 weeks ago

About

g0 is an open-source security control layer for AI agent systems, built by Guard0. It tackles three questions that most agent operators can't currently answer well: what agents do you have, what can they access, and can you demonstrate they're under control. The tool runs 1,200+ security rules across 12 domains mapped to OWASP, NIST, ISO, and EU AI Act frameworks, generates AI Bills of Materials in CycloneDX format, runs adversarial tests using 4,000+ attack payloads with CVSS scoring, and monitors agent fleets as a background daemon for security drift. It integrates into CI/CD pipelines via SARIF output for GitHub Code Scanning and supports 10 frameworks including LangChain, CrewAI, OpenAI Agents, and OpenClaw. Licensed under AGPL 3.0 with optional Guard0 Cloud for visualization.

person_check
Best For

Engineering teams deploying AI agents in regulated industries or any context where security governance and auditability matter. Also valuable for any team that wants to understand its agent attack surface before it becomes a production incident.

Pros & Cons

check_circle

Pros

  • check The combination of static assessment, adversarial testing, and continuous fleet monitoring covers the full security lifecycle rather than just point-in-time checks
  • check Compliance mapping to EU AI Act, OWASP, NIST, and ISO standards makes it a practical tool for teams with regulatory obligations, not just security hobbyists
  • check CI/CD integration with SARIF output means security gates can be enforced automatically before agents reach production
cancel

Cons

  • close AGPL 3.0 licensing has copyleft implications that some commercial teams will need to evaluate carefully before adopting
  • close The depth of coverage (1,200+ rules, 4,000+ payloads) means initial triage of findings can be time-consuming for teams new to AI security
  • close Full visualization and triage capabilities depend on the paid Guard0 Cloud service — the open-source tool alone has a less polished results experience

More Security

Other tools in the same category.

View All arrow_forward