A unified skill management and distribution hub that aggregates local skill folders and exposes them via MCP protocol to AI platforms, featuring lazy loading and hot reloading.
An enterprise MCP server scaffold that provides secure, governed access to internal tools through RBAC, audit logging, rate limiting, and prompt-injection boundaries, with a FastAPI control plane and OpenTelemetry observability.
A self-hostable semantic skill registry for AI agents, providing searchable, versioned, and verified skills over a single MCP endpoint with per-agent private vaults and trust tiers.
MCP server that adapts, activates, and shares local Agent Skills for runtimes like OpenAI Agents SDK and Claude Code, enabling dynamic discovery and shareable HTML/image artifacts.
A local-first skill runtime for AI coding agents that defines skills as verifiable, composable units with sandboxed execution, and exposes them as MCP tools over HTTP.