Observed arrival · 2026-08-31
AfterImage keeps timestamped copies of the pages AI agents get wrong
A paid API and MCP service that searches, fetches, and reuses readable copies of volatile web pages such as model catalogs, pricing tables, protocol specs, and changelogs.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
AfterImage separates searching stored material from fetching the live web: GET /v1/search does not make a live request, while GET /v1/page can reuse a copy when its max_age_s permits. Returned text is capped at 100,000 characters and carries both a fetched_at timestamp and SHA-256 hash. The service exposes the same key across HTTP, MCP, and balance checks, with cache hits priced below live fetches.
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