AITOPAI热报
How-toSelected

Engram AI memory system addresses chat history growth issues

Weaviate@weaviate_io
Post
View the post
Why we picked it

Engram's approach to managing AI memory could help developers build more reliable applications by preventing the slow-down and information conflicts that come from storing too much chat history.

Engram AI's new memory system handles AI memory by extracting key facts from raw messages, comparing them with existing memories, and storing a pruned set for retrieval. This process helps reconcile contradictions and updates, unlike treating chat history as an ever-growing pile that leads to slower responses and outdated information.

Image · Weaviate
Original · Weaviate

AI memory gets worse when you treat it as an ever-growing pile of chat history. Every turn adds more tokens, slower responses, and more outdated or contradictory information for the model to figure out at query time. People change their minds. Facts go stale. Eventually you have 50 memories about the same thing, all competing for space in the context window. @victorialslocum 's new video explains how 𝗘𝗻𝗴𝗿𝗮𝗺 handles this differently. Raw messages are sent to Engram, then asynchronous pipelines: 1️⃣ Extract the facts that matter 2️⃣ Compare them with existing memories 3️⃣ Reconcile contradictions, duplicates, and updates 4️⃣ Store a relevant, pruned set of memories for retrieval Developers control extraction with 𝗧𝗼𝗽𝗶𝗰𝘀, which are plain-language descriptions of what matters to the application. Memories are also fully scoped: • 𝗣𝗿𝗼𝗷𝗲𝗰𝘁-𝘄𝗶𝗱𝗲 for memories shared across a team of humans or agents • 𝗨𝘀𝗲𝗿-𝘀𝗰𝗼𝗽𝗲𝗱 for memories isolated to an individual • 𝗨𝘀𝗲𝗿-𝗮𝗻𝗱-𝗽𝗿𝗼𝗽𝗲𝗿𝘁𝘆 𝘀𝗰𝗼𝗽𝗲𝗱 for combinations like `user_id` + `conversation_id` The video also walks through setting up a basic user-scoped memory project: choose the personalization template, use the default pipeline, create an API key, and manage m youtu.be/kX9IhyltvuQ ns from the dashbo weaviate.io/product/engram… co/zfTE engram.playground.weaviate.io/?utm_source=ch… https://t.co/P4bsqEFCVQ Demo: https://t.co/Vp9PaG4Vfh Your browser does not support the video tag. 🔗 View on Twitter 💬 0 🔄 0 ❤️ 1 👀 109 📊 1 ⚡

#Engram#memory management#AI memory#chat history#prompt engineering

Keep reading

Recent stories with the same tag or section
PapersBuildersSelected09:30
GateRQ Quantizes DeepSeek Engram Memory Tables by Gate Weight

Frequency-based bit allocation is the wrong heuristic for conditional memory: gates, not access counts, predict which rows carry the facts that break when quantized. Engineers serving large hashed-memory models on vLLM get a drop-in path to 7.8x smaller GPU tables with near-baseline PopQA accuracy and no retraining. The method ties directly to DeepSeek-V4.1-Flash, where removing Engram costs 36.8 PopQA points, making memory-table compression a practical concern for anyone deploying that model.

#DeepSeek#GateRQ#quantization#long-tail knowledge
arXiv: DeepSeek@Tianqi Chen et al. (7)Source
PapersBuildersSelected14:52
STAPLE Adds Sparse Embedding Modules to Pretrained Checkpoints

Sparse upcycling usually means expensive retraining from scratch, so a method that grafts new capacity onto an existing checkpoint could cut the cost of scaling older models. The nuance matters: this is a lightweight FFN modification, not a full Engram architecture, so results depend on how much quality the added token-indexed embeddings recover. Researchers and engineers fine-tuning open-source checkpoints should follow the paper for the training recipe.

#STAPLE#sparse upcycling#fine-tuning#open-source models
Teortaxes@teortaxesTexSource