This might be the first open-source memory architecture to cover associative recall. The…
This is a dev post classified by Jev as Databases (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
This might be the first open-source memory architecture to cover associative recall. The rest stop at similarity search. (T-Mem, EMNLP 2026) Most memory systems retrieve by similarity. T-Mem predicts when a memory will matter, before you ask. → write: memories ship with a trigger at store time, basically "when will this come up again?" → read: at query time, triggers pull in memories by situation, even with zero keyword overlap. → architecture layer. plugs into any LLM without fine-tuning or model changes. On LoCoMo-Plus (strips keyword overlap, tests pure associative recall), mainstream sy
Posted by Tencent AI (24k followers) 1 days ago · 508 likes · 59.8k views · view the original post on X. Kept by the Dev Radar as Databases. Tools mentioned: t-mem.
More dev work like this
- Enterprise data can contain the answers you need, but it's often difficult to query… — @freeCodeCamp
- Nathan: — @benswerd
- Snowflake Adaptive Compute predicts each query’s performance curve before execution. — @Snowflake
- Reporting across SQL, spreadsheets, and APIs shouldn’t require a custom BI build. — @DanKornas
- Zero-Copy Interactive lets Interactive warehouses query your existing standard Snowflake… — @Snowflake
- Apache Spark 4.2 is out, and it adds vector primitives to Spark SQL: distance and… — @ApacheSpark
- Stop sending your coding agent into vector-search docs without a map. — @DanKornas
- Text classification in MotherDuck just got ~50x faster at ~1% of the cost. — @motherduck
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 20.7k posts from 4.9k X accounts over the last 21 days, 2.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 08:21 UTC. Full method.