An embedded, single-file database that combines graph relationships, vector similarity search, and full-text search — built for local AI, RAG, and agent-memory apps.
#search-engine
11 tools curated in this category — including LatticeDB, Anagnorisis, Histiq
techFind on mySelectas all sites and tools related to search-engine. This selection of 11 resources is reviewed and maintained by the community. The most popular include LatticeDB, Anagnorisis, Histiq. Each tool comes with a review, tags, comparisons and alternatives to help you make the best choice.
A self-hosted recommendation platform that builds a personalized content-discovery model on your own machine, trained only on your own ratings.
Histiq is a browser extension that lets you search your browsing history and saved PDFs using natural language, powered by local AI embeddings that never leave your device.
A paid, EU-based search engine with no ads, no tracking and no algorithms — you pay €5/month and it doesn't sell or profile your searches.
An iPhone app where you dump anything — a photo, a voice note, a screenshot, a bookmark — and find it later just by describing what it was about, no folders needed.
Adds a real search bar to your app or website without you having to run your own search server — upload your data, and it's instantly searchable, including by meaning, not just exact words.
Lets you search inside videos using plain English — like "find the scene where someone signs a contract" — instead of scrubbing through hours of footage or relying on manual tags someone forgot to add.
A search engine built for AI agents instead of humans — it hands back clean, structured answers instead of a page of blue links the agent then has to re-read and guess at.
A nonprofit's grant reports, board minutes and policy documents pile up over the years and become impossible to search by keyword — DocuSmart lets staff just ask a question in plain English and get an answer pulled from that pile.
Software that lets you search your own video and audio library by typing what you remember, without uploading any of it to the cloud.
Vector + full-text search database built on object storage: cheap at scale, sub-10ms latency, used by Cursor, Notion and Linear.