Observed arrival · 2026-10-10
RunLedger puts AI coding-agent runs on the record
An open-source CLI turns AI coding-agent sessions into shareable receipts and can block risky commands or request approval.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Teams reviewing AI coding-agent runs
- Worth noticing
- The guard uses Claude Code’s PreToolUse hook; team approvals require an admin with a different API key.
Field notes
The CLI reads an agent’s existing session log and keeps that recording on the user’s machine, according to the page. Risk scoring is described as rule-based, with reasons for individual points; the sample receipt includes a 0–100 score. The page separates its simulated dashboard walkthrough from displayed CLI test output, which shows a deny response for a recursive delete and an ask response for a sudo command.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue