AgentGate
A framework-agnostic, real-time human-in-the-loop approval layer — any agent calls one endpoint and waits for a human decision.
AgentGate gives AI agents a structured way to pause and ask a human before taking a consequential action. Any agent — LangChain, AutoGen, custom Python, Claude Code — fires a POST to /api/request, polls GET /api/status/:id, and receives the human's decision: approved, rejected, or modified with an inline JSON editor. The inbox runs in real time via Supabase Realtime WebSockets with live status indicators and pending-count badges. No SDK required — one HTTP request from any language.
The build log
Follow the work.
New essays and prototypes, in your feed reader. Email subscriptions are paused while I connect a working delivery service. No email is collected here.
Follow via RSS