I replaced vector databases with Git for AI memory (PoC)
Hey HN! I built a proof-of-concept for AI memory using Git instead of vector databases. The insight: Git already solved versioned document management. Why are we building complex vector stores when we could just use markdown files with Git's built-in diff/blame/history? How it works: Memories stored as markdown files in a Git repo Each conversation = one commit git diff shows how understanding evolves over time BM25 for search (no embeddings needed) LLMs generate search queries from conversation context Example: Ask "how has my project evolved?" and it uses git diff to show actual…
I replaced vector databases with Git for AI memory (PoC) launched on August 21, 2025 with 198 votes, #168 of 8,530 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
This proof-of-concept system stores AI conversation memory as markdown files in a Git repository instead of using traditional vector databases. It treats each conversation as a commit, uses Git's diff and history features to track how understanding evolves, and employs BM25 search without embeddings. Designed for developers and AI users seeking a simpler alternative to vector stores, it offers version control built-in and retrieves results sub-second while keeping a year's worth of conversations under 100MB of RAM. The creator notes it remains rough and experimental rather than production-ready.
written from the facts on this page · September 2026
From the sources
Git Based Memory Storage for Conversational AI Agent - Growth-Kinetics/DiffMem
In the maker’s words, at launch
Hey HN! I built a proof-of-concept for AI memory using Git instead of vector databases. The insight: Git already solved versioned document management. Why are we building complex vector stores when we could just use markdown files with Git's built-in diff/blame/history? How it works: Memories stored as…
Does a similar job
all alternatives →- WSWe scaled Git to support 1 TB repos2022 · xethub.com · ▲279
I’ve been in the MLOps space for ~10 years, and data is still the hardest unsolved open problem. Code is versioned using Git, data is stored somewhere else, and context often lives in a 3rd location like Slack or GDocs. This is why we built XetHub, a platform that enables teams to treat data like code, using Git. Unlike Git LFS, we don’t just store the files. We use content-defined chunking and Merkle Trees to dedupe against everything in history. This allows small changes in large files to be stored compactly. Read more here:…
Git for AI AgentsMay 2026 · github.com · ▲129hi guys. been working on something i think is fundamentally missing in today's workflow with ai agents. vcs. i find myself struggling with questions that agents can't answer like "why did you do it?", "when did u delete this folder? why?", etc. or trying to /rewind (after a /compact...) or basically `bisect` to find when and why something was done by the agent in the current / previous session. just like git did for code, i think we are the same core capabilities with ai agents so... i developed an open source solution for that (currently supporting claude code) would love to…
A Karpathy-style LLM wiki your agents maintain (Markdown and Git)Apr 2026 · github.com · ▲260I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet. It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you. The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard. I…
How we leapfrogged traditional vector based RAG with a 'language map'2024 · twitter.com · ▲162TL;DR: Vector-based RAG performs poorly for many real-world applications like codebase chats, and you should consider 'language maps'. Part of our mission at Mutable.ai is to make it much easier for developers to build and understand software. One of the natural ways to do this is to create a codebase chat, that answer questions about your repo and help you build features. It might seem simple to plug in your codebase into a state-of-the-art LLM, but LLMs have two limitations that make human-level assistance with code difficult: 1. They currently have context windows that are too small to…
GistrMay 2026 · gistr.so · ▲55Hey HN, We (a small team of engineers and a designer) have been building Gistr to solve a personal pain point: we consume a lot of content daily—articles, videos, podcasts—and often struggle to retain or revisit the most meaningful parts. Most bookmarking tools felt too passive or generic. So we made Gistr a tool that lets you save links and capture "gists" (notes, insights, highlights, AI summaries) on top of them. It supports YouTube, articles, PDFs, and more. You can keep things private or share your gists publicly, almost like AI-enhanced social bookmarks. We’re bootstrapped and still in…
A memory database that forgets, consolidates, and detects contradictionApr 2026 · github.com · ▲48Vector databases store memories. They don't manage them. After 10k memories, recall quality degrades because there's no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier. YantrikDB is a cognitive memory engine — embed it, run it as a server, or connect via MCP. It thinks about what it stores: consolidation collapses duplicate memories, contradiction detection flags incompatible facts, temporal decay with configurable half-life lets unimportant memories fade like human memory does. Single Rust binary. HTTP + binary wire protocol. 2-voter + 1-witness HA…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, August 2025
the whole month →
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
AI · 2025 · github.com
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca