OM2 launches persistent memory graph to cut the 50% of token bills spent re-reading company data

SucceededMind · x · 2026-09-04

coworker launched OM2, targeting a hidden cost of enterprise AI: models re-read the entire company for every query — Jira backlogs, 400 Slack messages, Salesforce history — then forget it all. The team claims over 50% of token spend goes to search, not answers. OM2 caches your tools into a persistent graph so the context is paid for once and reused across queries.

Related event: Coworker Launches OM2 Enterprise Memory Layer(2 posts)→

Original post →

More from coding & agent

coding & agent channel →