Cognee – Turn RAG and GraphRAG into custom dynamic semantic memory
Hey there HN! We’re Vasilije, Boris, and Laszlo, and we’re excited to introduce cognee, an open-source Python library that approaches building evolving semantic memory using knowledge graphs + data pipelines Before we built cognee, Vasilije(B Economics and Clinical Psychology) worked at a few unicorns (Omio, Zalando, Taxfix), while Boris managed large-scale applications in production at Pera and StuDocu. Laszlo joined after getting his PhD in Graph Theory at the University of Szeged. Using LLMs to connect to large datasets (RAG) has been popularized and has shown great promise.…
What it does
In the maker’s words, at launch
Hey there HN! We’re Vasilije, Boris, and Laszlo, and we’re excited to introduce cognee, an open-source Python library that approaches building evolving semantic memory using knowledge graphs + data pipelines Before we built cognee, Vasilije(B Economics and Clinical Psychology) worked at a few unicorns (Omio, Zalando, Taxfix), while Boris managed large-scale applications in production at Pera and StuDocu. Laszlo joined after getting his PhD in Graph Theory at the University of Szeged. Using LLMs to connect to large datasets (RAG) has been popularized and has shown great promise. Unfortunately, this approach doesn’t live up to the hype. Let’s assume we want to load a large repository from GitHub to a vector store. Connectingfiles in larger systems with RAG would fail because a fixed RAG limit is too constraining in longer dependency chains. While we need results that are aware of the context of the whole repository, RAG’s similarity-based retrieval does not capture the full context of interdependent files spread across the repository. This approach allows cognee to retrieve all relevant and correct context at inference time. For example, if `function A` in one file calls `function B` in another file, which calls `function C` in a third file, all code and summaries that further explain their position and purpose in that chain are served as context. As a result, the system has complete visibility into how different code parts work together within the repo. Last year, Microsoft took a leap published GraphRAG - i.e. RAG with Knowledge Graphs. We think it is the right direction. Our initial ideas were similar to this paper and this got some attention on Twitter (https://x.com/tricalt/status/1722216426709365024) Over time we understood we needed tooling to create dynamically evolving groups of graphs, cross-connected and evaluated together. Our tool is named after a process called cognification. We prefer the definition that Vakalo (1978) uses to explain that cognify represents "building a fitting (mental) picture" We believe that agents of tomorrow will require a correct dynamic “mental picture” or context to operate in a rapidly evolving landscape. To address this, we built ECL pipelines, where we do the following: - Extract data from various sources using dlt and existing frameworks - Cognify - create a graph/vector representation of the data - Load - store the data in the vector (in this case our partner FalkorDB), graph, and relational stores We can also continuously feed the graph with new information, and when testing this approach we found that on HotpotQA, with human labeling, we achieved 87% answer accuracy (https://docs.cognee.ai/evaluations). To show how the approach works we did an integration with continue.dev and built a codegraph Here is how codegraph was implemented: We're explicitly including repository structure details and integrating custom dependency graph versions. Think of it as a more insightful way to understand your codebase's architecture. By transforming dependency graphs into knowledge graphs, we're creating a quick, graph-based version of tools like tree-sitter. This means faster and more accurate code analysis. We worked on modeling causal relationships within code and enriching them with LLMs. This helps you understand how different parts of your code influence each other. We created graph skeletons in memory which allows us to perform various operations on graphs and power custom retrievers. If you want to integrate cognee into your systems or have a look at codegraph, our GitHub repository is (https://github.com/topoteretes/cognee) Thank you for reading! We’re definitely early and welcome your ideas and experiences as it relates to agents, graphs, evals, and human+LLM memory.
Does the same job
all alternatives →- COCognee – Open-Source AI Memory Layer That Remembers Context2025 · github.com · ▲9
Hey HN! We're Vasilije, Laszlo and Lazar, the authors of a new paper and part of https://www.cognee.ai. cognee let’s you build memory layers for AI applications and agents, allowing them to personalize results, connect various data sources, and add custom rules. This enables AI apps to deliver increasingly accurate responses, we reached almost 90% on standard industry benchmarks as you can see here https://github.com/topoteretes/cognee/tree/main/evals and our paper can be accessed at: https://arxiv.org/abs/2505.24478 and collab…
- AOAuto-optimizing deterministic LLM outputs using knowledge graphs2024 · github.com · ▲7
Hi, We are building an open-source framework for loading and structuring LLM context to create accurate and explainable LLM answers using knowledge graphs and vector stores. We built the tool with four main concepts in mind: 1. Loader -> uses dlt in the backend to load and structure the data 2. Cognify step -> creates a graph with summaries, labels and factoids that are interconnected across the documents and stored as a representation in the vector store 3. Optimizer -> Uses DSPy to optimize LLM queries, and we plan to extend it to most of the knobs we can turn, like chunking etc. 4. Search…
- BLBuild Live AI and RAG Pipelines in Minutes with YAML Templates2024 · pathway.com · ▲8
Hello everyone! I am Jan, CTO and one of the creators of Pathway, the real-time data processing framework. I’m excited to share Pathway’s ready-to-use AI Pipelines, configurable with just YAML! These frameworks offer out-of-the-box solutions for AI search, RAG, and more—optimized for real-time indexing and in-memory processing. What makes it simple? YAML templates! The pipeline templates are fully customizable using YAMLs to fit your needs, from changing the data sources to the choice of the LLM model, all without touching Pathway’s Python code. Thanks to the Pathway data processing engine,…
- PPPython package for generating accurate SQL via LLMs using RAG2023 · github.com · ▲7
Hello HN! We’ve been working hard on Vanna, our RAG framework for SQL generation and we’ve been updating our documentation. Please have a look — we have a ton of Jupyter notebooks for any combination of desired use cases. At it’s heart, we have abstractions that help you: - “train” a RAG “model” i.e. add metadata for the retrieval augmentation system to reference when constructing the LLM prompt (yes, we know that the terms “train” and “model” are somewhat confusing and we’re open to changing those terms if you can suggest better ones) - “ask” questions, which will generate SQL, run it,…
- UIUSearch Images demo in 200 lines of Python2023 · usearch-images.com · ▲9
Hey everyone! I am excited to share updates on four of my & my teams' open-source projects that take large-scale search systems to the next level: USearch, UForm, UCall, and StringZilla. These projects are designed to work seamlessly together, end-to-end—covering everything from indexing and AI to storage and networking. And yeah, they're optimized for x86 AVX2/512 and Arm NEON/SVE hardware. USearch [1]: Think of it as Meta FAISS on steroids. It's now quicker, supports clustering of any granularity, and offers multi-index lookups. Plus, it's got more native bindings than probably…
- MMMulti-modal RAG with ColQwen in a single line of Code2025 · github.com · ▲5
Hi HN, we're Arnav and Adi, and we're building DataBridge - a multi-modal database built from the ground up with AI use cases in mind. We recently launched support for ColPali-style image embeddings and late-interaction retrieval. We've implemented a hamming distance version of retrieval which helps this approach scale significantly more when compared with the regular late-interaction similarity scoring. These embeddings provide a significantly better retrieval accuracy, with ColQwen achieving around an 89% average score on the ViDoRe benchmark, compared to around 67% for traditional parsing…
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 · 26d ago · cactuscompute.com
Launched alongside, February 2025
the whole month →
Screen Studio 3.0▲1,833Beautiful screen recordings with instant shareable links
Growth · 2025 · screen.studio
- IG
I was at FB/Meta from late 2013 to early 2023, mostly working in the compiler/runtime spaces. I got hit in the spring 2023 layoff wave. I immediately started making games in my newfound free time (a lifelong interest, and I even worked in AA(A?) back ca. ~2000), and in October 2023 I stumbled upon the idea of a roguelike pachinko/plinko game inspired by Luck Be A Landlord. Things snowballed quickly, I started talking to publishers, then worked like crazy through all of 2024, almost the hardest I've ever worked in my career, and launched the game in December 2024. It's sold…
Work · 2025
- IB
i wanted to change the habit of reaching for my phone in the morning and doomscrolling away an hour so i built an app to help me. now i have to literally touch grass before accessing my most distracting apps the app is built in swiftui, uses the screen time apis provided by apple and google vision to recognise grass or not i'd love to get your thoughts on the concept.
Life & fun · 2025 · touchgrass.now