ClawJetty: See what your AI Agent is Doing
No-SDK agent tracking: paste a prompt, get a live public status URL.

Public status pages for AI agents when LangSmith is just for devs.
AI application developers building autonomous agents
LangSmith · LangFuse · Helicone
No-SDK agent tracking: paste a prompt, get a live public status URL.
This is one of the clearer, money‑moving agent demos I’ve seen: the agent persists memory as markdown, runs on Claude/OpenClaw, wires Telegram for comms and Gumroad for payments, and even bought X Premium after evaluating ROI. It’s not a full product so much as a living experiment — but the end‑to‑end automation (domain, store, monitoring cron jobs, live revenue tracker) makes the demo feel legitimately capable rather than academic.
SQLite-backed MCP server gives local agents shared memory without vector DB overhead.
Knowledge graph compression (3,714x token ratio) is impressive, but 'persistent agent memory' is crowded territory.
5-level memory hierarchy for AI agents, but MCP ecosystem is early and adoption unclear.
Fixes real agent deployment pain — but Replicate, Modal, and Railway already do this well.