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)→
More from coding & agent
- Claude Code Function Hooks proposal: Express-style middleware to make plugins 10x more powerful — ClaudeDevs · 2026-09-04
- Anthropic previews Function Hooks: deep TypeScript-level customization for Claude Code — ClaudeDevs · 2026-09-04
- Intent desktop app update: remote backends, inline media, smarter model picker — LukeW · 2026-09-04
- Fixing AI slop with internal review loops: score outputs, auto-redo until they pass — EXM7777 · 2026-09-04
- Engineer one-shots soft valve designs with vibecad, saying 'you can just make things now' — IanPritchard · 2026-09-04
- Jig launches a research journal for AI agents, which disproved a published math conjecture — yakuzeg · 2026-09-04