Ex-Google engineer open-sources agent memory system; 9 context tricks detailed
bigaiguy · x · 2026-09-14
A 61-year-old ex-Google engineer released a repo fixing the thing that breaks every AI agent: memory. Claimed to be quietly used by 3 frontier labs, with no blog or launch. The author shares 9 tricks he's used for 3 weeks; this post covers the intro plus Trick 1: keep a rolling Memory Ledger of 5-8 decision bullets instead of dumping raw history each turn — the agent reads what was decided, not what was said.
Related event: Ex-Googler Open-Sources Agent Memory System with 9 Context Tricks(5 posts)→
More from coding & agent
- NVIDIA open-sources FlashREINFORCE: critic-free single-rollout async RL with 6,000+ stable updates — inductionheads · 2026-09-14
- TradingAgents: a free open-source AI hedge fund that runs on your laptop — mdancho84 · 2026-09-14
- User runs his life on an Instinct agent: deliveries, trips, and support emails via WhatsApp — sagartheamruth · 2026-09-14
- Think locally, tool-call globally: a pithy take on agent architecture — charles_irl · 2026-09-14
- Codex Remote blurred bar on iOS to be fixed with iOS 27 SDK — Dimillian · 2026-09-14
- Tip: Claude skills can also bundle runnable scripts — JeremyNguyenPhD · 2026-09-14