LLM Memory Storage that scales, easily integrates, and is smart
I built a super easy to integrate memory storage and retrieval system for NodeJS projects because I saw a need for information to be shared and persisted across LLM chat sessions (and many other LLM feature interactions). I tried to keep the barrier to use as low as possible so I included built-in support for major LLMs (GPT, Gemini, and Claude) as well as major vector store providers (Weaviate and Pinecone). The memory store works by ingesting and automatically extracting “memories” (summarized single bits of information) from LLM interactions and vectorizing those. When you want to provide…
What it does
In the maker’s words, at launch
I built a super easy to integrate memory storage and retrieval system for NodeJS projects because I saw a need for information to be shared and persisted across LLM chat sessions (and many other LLM feature interactions). I tried to keep the barrier to use as low as possible so I included built-in support for major LLMs (GPT, Gemini, and Claude) as well as major vector store providers (Weaviate and Pinecone). The memory store works by ingesting and automatically extracting “memories” (summarized single bits of information) from LLM interactions and vectorizing those. When you want to provide relevant context back to the LLM (before a new chat session starts or even after every user request) you just pass the conversation context to the recall method and an LLM quickly searches the vector store and returns only the most relevant memories. This way, we don’t run context size issues as the history and number of memories grows but we ensure that the LLM always has access to the most important context. There’s a lot more I could talk about (like the deduping system or the extremely configurable pieces of the system), but I’ll leave it at that and point you to the README if you’d like to learn more! Also check out the dev client if you’d like to test out the memory palace yourself!
Does the same job
all alternatives →
- ZLZep – Long-Term Memory Store for LLM Apps2023 · ▲7
Zep is a long-term memory store designed for conversational AI applications built using modern LLMs. It handles the storage, summarization, embedding, indexing, and enrichment of chat histories, and offers developers a simple, low-latency API to this data. Chat history storage is an infrastructure challenge all developers and enterprises face as they look to move from prototypes to deploying conversational AI applications that provide rich and intimate experiences to users. Key features include long-term memory persistence, auto-summarization, vector search, auto-token counting, and Python…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
