Coworker launches OM2: enterprise memory layer + model routing claims 51x cost cut
FellMentKE · x · 2026-09-03
Coworker AI launched OM2, a permanent memory layer for enterprise AI agents. Today's agents re-search Slack, docs, and CRM from scratch every task — over 50% of the token bill goes to searching for context, not the answer. OM2 gives AI a persistent memory of the company; the company claims it makes enterprise AI 9x cheaper, and 51x with model routing that sends each request to the right model, with 84.5% better quality (per their benchmarks vs. Claude native tooling). Available via Coworker MCP (works in Claude Code, Cursor, any MCP client, 50+ tools) or native apps; SOC 2, 50+ connectors.
More from coding & agent
- How I Wrangle AI Agents — a practitioner writeup — dfinke · 2026-09-04
- One founder turned his endless idea backlog into an AI-built public archive site — Delahuntagram · 2026-09-04
- Teacher With 16GB VRAM Hits a Wall: Local LLMs Keep Failing at MCP Tool Use — whakahere · 2026-09-03
- ComfyUI-Minimax-H3-Promptor v1.5 Adds Shot-Level Refine, Autocomplete, Local GGUF — Narrow-Particular202 · 2026-09-03
- OpenClaw 2.0 adds per-user OAuth for MCP servers, enabling multiplayer shared bots — steipete · 2026-09-03
- PRs NOT Welcome: Vercel, tldraw and Flue replace community PRs with agent software factories — rseroter · 2026-09-03