Glen: Org-Wide Memory Layer for Agents Cuts Context by 29%

ycombinator · x · 2026-08-21

Glen builds an organizational learning and context layer for agents, preventing the loss of reasoning after sessions close. It unifies sessions from Claude Code, Codex, Cursor, and data from Slack, GitHub, tickets, and docs. When a new agent starts a task, Glen finds and injects relevant prior context. Benchmarks show a 29% reduction in context usage and 21% speed improvement, with features like dynamic skill distillation and multiplayer agents.

Original post →

More from coding & agent

coding & agent channel →