Show HN: ClawDiary – Audit log and human approval gate for AI agents (Claw, MCP
Hacker News Show AI
•
Generative AI
ClawDiary is an audit diary and guard for AI agents. I use Cursor a lot and wanted something that (a) logs what the agent does and (b) blocks dangerous actions until I approve them in Telegram. What it does: - Audit: agents POST to /v1/audit after each action; writes go to D1 async so the agent isn’t blocked. - Guard: before risky ops (rm, drop table, execute_bash, transfer, etc.) the agent calls /v1/guard. Request is d and the call blocks until you approve or reject in Telegram (or by updating DB). Green-light actions return immediately.