MindsDB is an AI analytics platform that lets users query data from over 200 connected sources using natural language. It is designed to produce insights and dashboards without moving data through ETL processes.
rtrvr.ai is a web automation tool that uses AI to retrieve structured data, run research across multiple browser tabs, and automate browser tasks. It runs as a DOM-based browser agent in Chrome and supports workflows such as lead extraction and CRM integration.
Vectorize is a RAG-as-a-Service platform that extracts text, images and tables from documents such as PDFs and Word files and builds optimized vector search indexes for AI applications. It offers a retrieval API, re-ranking and a no-code interface, and it can connect to external data sources.
Kapa.ai is a platform that turns technical documentation and knowledge bases into AI assistants that answer product questions. It integrates with tools such as Slack, Discord and documentation systems, and includes analytics on user queries and content gaps.
Pico is a lightweight open toolkit for training and analyzing language models, built around the pico-train and pico-analyze libraries. It provides a model suite from 11 million to 570 million parameters and tools for studying learning dynamics such as convergence rates, effective rank and gradient magnitudes.
Chat2DB is an AI-powered SQL client that converts natural language into SQL queries and supports databases such as MySQL, Redis and MongoDB. It also offers a graphical interface for managing data, schema migration and AI-generated charts and dashboards.
Dumpling AI is a platform that provides AI agents and automations with structured, LLM-ready data scraped from sources such as YouTube, Google search, Google Maps, documents and media files. It also offers tools for converting files to text, trimming MP4 videos and running JavaScript code.
Massed Compute is a cloud computing service offering bare metal servers, on-demand GPU and CPU rentals, and an Inventory API for provisioning NVIDIA GPU instances. It is aimed at AI training, machine learning, HPC, and data analysis workloads.
A starter codebase for building a reusable prompt library with Marimo reactive notebooks. It provides notebooks for ad-hoc prompting, testing prompts across multiple language models, and ranking models by performance.
llm is a command-line utility and Python library for interacting with large language models. It runs prompts from the terminal, works with local and remote models, stores outputs in SQLite, and supports embeddings.
Galileo AI is a data analysis platform that uses machine learning for predictive analytics, classification, regression and clustering. It offers integrations with existing data sources and APIs for developers.