Welcome to Try It and let us know What You Think

vector search solutions mentioned in this post:

Milvus

Qdrant

Weviate

Open Search

Pgvector

Redis

Cassandra

Solr

Vespa

Pinecone

Vertex AI

Are hallucinations really simply failures?

any thoughts?

it's annoying to me that there's not a doc store with vectors. seems like the vector dbs just store the vectors I think.

Elasticsearch and MongoDB Atlas and PostgreSQL and SQLite all have vector indexes these days.

My search service Lens returns exact spans from search, while having the best performance both in terms of latency and precision/recall within a budget. I'm just working on release cleanup and final benchmark validation so hopefully I can get it in your hands soon.

Pinecone allows 40k of metadata with each vector which is often enough.

Elasticsearch and Vespa both fit the bill for this, if your scale grows beyond the purpose-built vector stores.

chroma stores both

As does Azure's AI search.

I just use sqlite

This looks pretty cool

I am not a designer but i used figma a lot for website projects. It is good but it took sooooooo long to load the files... even though I downloaded a desktop, still very slow.. anybody met with the same issue?

thank you. welcome to try it and let us know what you think about it. Any feedback is welcome, positive or negative.

I do not work for Cluely. I am just impressed by what they've done, which is controversial but impressive.

I'm also impressed by how fast this team grows and generates revenue ($7M ARR now and $ 15M seed funding by A16Z, but rejected by Y Combinator. Aha, another drama), and, of course, by some of the bold statements they made.

Interestingly, though controversial, their user base never stops growing. Their product charges only $20 a month, but they got $7M ARR, which roughly means they got 350K users. Amazing.

Some numbers I found: https://techcrunch.com/2025/07/03/cluelys-arr-doubled-in-a-w...

https://techcrunch.com/2025/06/20/cluely-a-startup-that-help...

It is brilliant marketing.