A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
turbopuffer: fast search on object storage
Inaugural blog post about the development of turbopuffer, a search engine that uses object storage and SSD caching for cost-effective, low latency search. This post describes into the motivation behind its creation, its unique architecture, and how it significantly reduces costs for large-scale vector searches. Discover how turbopuffer is transforming search infrastructure for companies like Cursor and Suno, offering a scalable and reliable solution.
Spacedrive — A local-first data engine for everything you own
Index any data source. Search everything from one place. Keep it on your machine.
IndieSearch
I built a prototype for client-side, fully distributed search for the IndieWeb — check out the demo & a little explainer.
Meilisearch: Unified Search & AI Retrieval Platform
Build lightning-fast search and AI retrieval with Meilisearch. Open-source, developer-friendly search engine trusted by 20,000+ teams worldwide.
ParadeDB — Search without a second system
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
Why Google’s New AI-Saturated Search Page Will Be A Disaster
Google didn’t invent full-text search of the Internet – that honor belongs to early pioneers such as WebCrawler, Lycos and AltaVista. But for the last 25 years or so, Google has…
Fast regex search: indexing text for agent tools · Cursor
How we're building indexes for regular expression search so agents can find text in large monorepos without the 15-second ripgrep waits.
Building a Smarter AI Agent with Neural RAG - Will Bryk, Exa.ai
Parallel Web Systems | Infrastructure for intelligence on the web
Parallel's new FindAll API turns natural language queries into custom datasets from the web. It finds entities like companies, people, or locations based on your criteria, then enriches them with structured data—all with citations. FindAll Pro achieves 61% recall, 3x better than competitors.
Fixing Search
Search on the web, for most people, has become a deplorable experience. It is such a key function that it can feel unfixable, but by treating search as an architectural component of the web (which it effectively is) and working our way through the issues it creates, we can define an alternative that is both realistic and superior.
Standard Search
A search engine for standard.site posts, indexing documents published on AT Protocol.
👋 Jan on Twitter / X
Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro.In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally.Use cases:- Web search- Deep ResearchBuilt on the new version… pic.twitter.com/YApIShOAHI— 👋 Jan (@jandotai) August 12, 2025
Karpathy shares 'LLM Knowledge Base' architecture that bypasses RAG with an evolving markdown library maintained by AI
Karpathy proposes something simpler and more loosely, messily elegant than the typical enterprise solution of a vector database and RAG pipeline.
Here's how we leverage @semble.so's wonderful service in search results 👀. This is currently the only working search integration but 20+ more are in the works right now!
Search engines
Features and comparisons for when I’m “search engine shopping” and not so much about enshittification etc. Currently I mostly use DuckDuckGo (for when I basically know what I’m looking for) and Kagi (for when I don’t or if I’m dissatisfied with DDG; I’m not on their unlimited plan).
あ (@aiueo.ooo)
Google’s AI search is so broken it can ‘disregard’ what you’re looking for
Google Search’s AI evolution includes more ads
Searching for 'Disregard' Breaks Google [Updated]
あ (@aiueo.ooo)
