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.
More from coding & agent
- effect-harness on Cloudflare: run agent loops, tools and credentials on separate VMs — samgoodwin89 · 2026-10-31
- jh3yy: agents gave me flow state — my tools finally keep up with my brain — jh3yy · 2026-10-31
- CAFE ecosystem: Maple moves 300k lines of React to Foldkit in 3 days — samgoodwin89 · 2026-10-31
- Non-coder builds 100-star Android TV launcher entirely with Claude — SuB8u · 2026-10-31
- Factory acquires typedef_ai to give coding agents an enterprise data context layer — maddiehfaulkner · 2026-10-31
- Browser agent's graph reroute wins 5/5 vs 0/5 for trajectory replay, author retracts own number — JeremyCMorgan · 2026-10-31