Security / AI Agent Security
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.
The page clearly describes an AI-adjacent developer security product with concrete functionality, supported agents, and operating model. The repository README shows enough evidence for a useful public listing: what it does, how it works, what it stops, and which agents and approval channels it supports.
The crawl does not show installation steps, usage examples, screenshots, or release status, so a visitor still cannot tell how hard it is to set up or what the day-to-day workflow looks like in practice.
Last evaluated 23 days ago. Current rank #180. 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.
