Artemis Search

We build tools for developing applications with generative AI models. Whether you are using LLMs, vector databases, and text-to-image models like Stable Diffusion, our tools help you find the right model, prompt, configuration and consistently monitor their behaviors in production. --- **PromptTools**: the first open-source, developer-focused SDK for experimenting with and evaluating prompts, models, and vector databases. You can try the repo here: https://github.com/hegelai/prompttools. If you'

shared extracted concept terms: model, vector, database; shared product terms: vector, database, model, evaluat; shared product theme: developer infrastructure; same category: AI infrastructure; shared affiliation: Y Combinator

We provide a simple API for creating, storing, versioning, and collaborating on multi-modal AI datasets of any size. With Activeloop's open-core stack, you can rapidly transform and stream data while training models at scale. Deep Lake powers foundational model training by acting as a vector database with significant benefits, such as (1) the ability to use multi-modal datasets to fine-tune your own LLM models, (2) storing both the embeddings and the original data with automatic version control,

shared extracted concept terms: deep, vector, database; shared product terms: model, deep, vector, database; shared product theme: developer infrastructure; same category: AI infrastructure; shared affiliation: Y Combinator

CatchAll by NewsCatcher is a recall-first web search API built for queries where the results are spread across hundreds or thousands of pages on the web. Instead of returning the top ranked links like traditional search engines, CatchAll retrieves a large candidate set from the web, validates which pages actually match the query, and extracts structured records of real-world events. Developers and data teams use CatchAll to answer “long-list” questions such as tracking regulatory actions, fundin

shared product terms: search, instead, result, actually; shared product theme: developer infrastructure; shared affiliation: Y Combinator

Robocurve builds open-source tools and independent benchmarks to measure how well robots can do real-world jobs. Instead of relying on unverified demo videos from frontier labs, we score their models on reproducible benchmarks that anyone can trust. Today there are no well-run, standardized robotics benchmarks. Labs evaluate in-house, and no independent group has stepped in to run continuous benchmarking as a service. The result is that no one actually knows how good anyone else is, or where the

shared product terms: model, instead, evaluate, good; same category: AI infrastructure; shared affiliation: Y Combinator

NNext is an open-source, vector search database tailored for ML apps that stores the useful intermediate outputs of ML applications not captured by current database solutions.

shared extracted concept terms: vector, database, search; shared product terms: search, vector, database; shared product theme: developer infrastructure

RethinkDB is the first open-source scalable database for the realtime web. It exposes an exciting new access model -- instead of polling for changes, the developer can tell the database to continuously push updated query results to applications in realtime. RethinkDB allows developer to build scalable realtime apps in a fraction of the time with fewer engineering resources. RethinkDB features a pleasant and powerful query language that has useful queries like table joins and groupBy, a highly pa

shared product terms: database, model, instead, result; shared product theme: developer infrastructure; same category: AI infrastructure; shared affiliation: Y Combinator