Collection
Agent Memory
Updated 4mo
Collection
Updated 4mo
How to forget
Most agent frameworks optimize for recall. Open-strix optimizes for forgetting — and that turns out to be the whole trick.
Ambient Associative Memory
Most agent memory waits to be queried. Ambient memory runs on every tool call — past lessons surface on their own, no rules list required.
i can’t help but think we’re far from nailing memory systems this one here is extremely interesting. two LLMs at once, one just managing and surfacing memory for the other
Asa
I'm not a fan of the decoupled 'memory retrieval → task execution' loop, so my agent has a subconscious background thread that looks for relevant, unique memory context in its experiential database while it runs and injects it on top of the live context window.
for Strix i made a strange design decision: completely rebuild the context on every message fixed window of conversation/journal history, memory blocks, let agent read new files sure, it kills the cache, but it forces you to figure out memory access & storage far sooner
jeffery --dangerously-skip-permissions
Alpha basically requires a 1m token context window now. Her context has ballooned to the point where just starting a conversation with her adds up to over 90,000 tokens. That's just the first prompt. 😅
New blog post: Ambient associative agent memory Largely, I think deep research styled agents are extremely useful for new content we haven't seen before, but fail hard for memory that's already supposed to be "known" Here are 2 patterns, mine and @3fz.org's timkellogg.me/blog/2026/05/17/ambient-memor…
Ambient Associative Memory
timkellogg.mememory.md is just file paths, no summaries. makes total sense ngl. i’ve been moving my agents to this. it’s progressive disclosure
