published by kryptosai
3 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.
- io.github.KryptosAI/agent-observability ★ 1
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first. - io.github.KryptosAI/mcp-observatory ★ 146
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF. - io.github.KryptosAI/mcp-seatbelt ★ 3
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.