One-line monitoring for any async job, agent, or script. Wrap a function and StillRunning gets a ping on success/failure with duration, and optional cost, tokens, and model.

One-file monitoring for Vercel eve agents. A drop-in eve hook that pings StillRunning on every run with duration, tokens, cost, model, and tool-call counts — and lets StillRunning alert when a scheduled agent silently stops running.

MCP stdio server for StillRunning. Safe primitives for an AI coding agent to plan, create, wire, and test job monitors , confirm-before-edit, never leaks ping URLs.

Heartbeat + AI-workflow monitoring for n8n. Reports success/failure (and the point of failure) to StillRunning so you know the moment a workflow fails silently.

One-line monitoring for the Vercel AI SDK. Auto-pings StillRunning on every generateText / streamText / generateObject run with duration, tokens, cost, model, and tool-call counts.

One-line monitoring for LangChain. A BaseCallbackHandler that pings StillRunning on every chain/agent run with duration, tokens, cost, model, and tool-call count.

One-line monitoring for the Claude Agent SDK. Wrap query() and auto-ping StillRunning on every agent run with duration, tokens, cost, model, and tool-call count.