Alternatives
Products that do what Breathe-Memory – Associative memory injection for LLMs (not RAG) does
LLMs forget. The standard fix is RAG — retrieve chunks, stuff them in. It works until it doesn't: irrelevant chunks waste tokens, summaries lose structure, and nothing actually models how memory works. Breathe-memory takes a different approach: associative injection. Before each LLM call, it extracts anchors from the user's message (entities, temporal references, emotional signals), traverses a concept graph via BFS, runs optional vector search, and injects only what's relevant — typically in <60ms. When context fills up, instead of summarizing, it extracts a structured graph: topics,…
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10ZL
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…
2023
- 11YP
It's an biological inspired decay system for our memories with extended support of temporal reasoning. Created a CLI command to infer knowledge from the context stored in memory system without any token utilization or llm call. It comes with a memory dashboard to monitor and manage your memories it can be extended as audit trail for agents as well !
May 2026
- 12FL
Long-session LLM memory degradation (entropy) is the silent killer of complex coding projects. Models like Gemini, GPT-4, and Claude all suffer from it, leading to hallucinations and lost context. I've developed an open-source protocol that temporarily "fixes" this issue by structuring the dialogue. It's not the final architectural solution, but it’s a proven patch for developers working right now. Looking for feedback from the community on how we can solve this structurally. https://github.com/robertomisuraca-blip/LLM-Entropy-Fix-Prot...
Nov 2025 · github.com
- 13AI
Hi I am Jan, CTO @ Pathway. A use case we have been working on with LLMs is to let people know when an answer to their query changes due to revisions of source documents. Obviously, we want to avoid periodically re-computing all queries for the LLM. Why I think it’s cool? - We don’t spin in a loop to repeat with the LLM. - Alerts are LLM-deduplicated - no spamming users with typo fixes - And the best - our framework, Pathway takes care of handling the updates, the example looks nearly like a regular, static RAG chatbot. More context + GIF of how it works for Google Drive document alerts:…
2023 · github.com
- 14LM
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…
Mar 2026 · github.com
- 15IM
Live demo here: http://fonctionlabs.com:8000 Similarly to aka_sh (guess we were working parallelly on similar topics), I created with my brother a chainlit-based webapp, which summarizes Youtube videos in order to gain time. It works as an RAG-based LLM, and is very light in the sense that it does not use RAG libraries like langchain or llamaindex. You can use it with your own OpenAI API key. It also supports local models like Mistral, or Llamma. It is ofc open-source, and you can deploy with Docker if you choose. Some of the next steps are: - using whisper to be able to compute a…
2024 · github.com
- 16PR
Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch/transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!
Dec 2025 · github.com
- 17IC
RAG pipelines have become bloated: embeddings, vector DBs, rerankers, and ad-hoc pipelines everywhere. Projects like Claude Code showed a simpler path: In-Context Retrieval — letting the LLM reason directly over context for retrieval instead of outsourcing search to external infrastructure. PageIndex takes that one step further with In-Context Indexing. If retrieval happens in-context, the index should live there too. Each document is transformed into a hierarchical, human-readable tree structure (like a table-of-contents tree index) inside the model's context window. The LLM reads the…
Oct 2025 · github.com
- 18LP
I was not getting good cache utilization when including dynamic context in agent threads. After a lot of experimentation, I found a good pattern that minimizes how often long lived conversation history gets modified while still supporting dynamic context. It has flexible hooks for doing things like truncating or summarizing tool outputs when transitioning messages to the long term history. And I'm seeing >>90% of tokens hitting the cache for my agents despite including a lot of dynamic user context. There are a wide range of agent prompting strategies so I'd love to hear where this library…
Jun 2026 · github.com
- 19UM
Hi HN, We’ve been building memU(https://github.com/NevaMind-AI/memU), an open-source, general-purpose memory framework for AI agents. It supports dual-mode retrieval: classic RAG and LLM-based direct file reading. Most multimodal memory systems either embed everything into vectors or treat non-text data as attachments. These work, but at scale it becomes hard to explain why certain context was retrieved and what evidence it relies on. memU takes a different approach: since models reason in language, multimodal memory should converge into structured, queryable text, while…
Jan 2026 · github.com
- 20CR
hi everyone. how does moving llm call prompts and output structure definitions away from code into configuration land sound? would you use something like this if it was stable and well documented enough? please don't hold back the criticism. i appreciate all feedback (constructive & otherwise).
2024 · github.com
- 21SE
I built a CLI tool in Go that extracts structured data (JSON, CSV, Parquet) from messy PDFs and HTML pages. The core idea: LLMs are great at understanding structure but wasteful for bulk data extraction. So smelt uses a two-pass architecture: 1. A fast Go capture layer parses the document and detects table-like regions 2. Those regions (not the whole document) get sent to Claude for schema inference — column names, types, nesting 3. The Go layer then does deterministic extraction using the inferred schema This means the LLM is never in the hot path of actual data processing. It figures out…
Mar 2026 · github.com
- 22AO
I've built an airgapped Retrieval-Augmented Generation (RAG) system for question-answering on documents, running entirely offline with local inference. Using Llama 3, Mistral, and Gemini, this setup allows secure, private NLP on your own machine. Perfect for researchers, data scientists, and developers who need to process sensitive data without cloud dependencies. Built with Llama C++, LangChain, and Streamlit, it supports quantized models and provides a sleek UI for document processing. Check it out, contribute, or suggest new features!
2024 · github.com
- 23MA
Hey HN! I built Memoripy, a memory layer for AI that adds short-term, long-term, and semantic memory capabilities to enhance LLM applications. It helps AI systems retain and prioritize past interactions, adapt over time, and respond with greater context and personalization. Memoripy uses semantic clustering to retrieve relevant memories, along with adaptive memory decay and reinforcement, so interactions stay fresh and context-aware. It’s designed for easy integration with OpenAI, Ollama, and other platforms—giving your AI applications dynamic memory management with minimal setup. Would love…
2024 · github.com
- 24OS
Hello HN, I’ve been building AI agents lately and ran into a common "Context Bloat" problem. When an agent has 20+ skills, stuffing every system prompt, reference doc, and tool definition into a single request quickly hits token limits and degrades model performance (the "lost in the middle" problem). To solve this, I built OpenSkills, an open-source SDK that implements a Progressive Disclosure Architecture for agent skills. The Core Concept: Instead of loading everything upfront, OpenSkills splits a skill into three layers: Layer 1 (Metadata): Light-weight tags and triggers (always loaded…
Jan 2026
Ranked by how close each launch is in meaning, then by votes. Refine with a description →