Security / Endpoint Security
Open-source endpoint visibility and response for AI agents, with local detection, optional pre-action blocking, and forensic reconstruction.
The snapshot shows a real, well-described security tool for AI agent activity on endpoints. The README explains what it does, how it works, supported surfaces, installation options, and concrete commands for monitoring, scanning, and hook-based enforcement. It is useful for AI builders and security teams, and the combination of local detection, optional blocking, and forensic reconstruction gives it a strong, distinct use case.
The crawl does not show the full coverage matrix, the enforcement guide, or the architecture details needed to tell exactly which agents and hooks are supported beyond the examples shown. It also does not show release history, docs depth, or maintenance cadence from the page itself.
Last evaluated 32 days ago. Current rank #649. Down 3 spots in the rankings.
Open-source security scanner for AI agents, MCP servers, and agent skills. It auto-discovers installed agent components and checks them for prompt injection, tool poisoning, secrets, malware payloads, and related risks.
Self-hosted AI security testing platform for authorized pentesting and bug bounty workflows, with a local web UI, live agent telemetry, verified findings, and branded PDF reports.
GitHub Marketplace app from NeuraLegion that scans apps and APIs for vulnerabilities, proposes fixes, and validates remediations inside GitHub workflows.
Belay is an open-source, local-first security layer for AI coding agents. It blocks dangerous commands, secret leaks, prompt injection, and risky MCP tool calls, with human approval flows and support for multiple agents.
