Postgres with GPUs for ML/AI apps.

All-in-one AI CLI tool featuring Chat-REPL, Shell Assistant, RAG, AI tools & agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

All-in-one infrastructure for search, recommendations, RAG, and analytics offered via API

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

The simplest way to build AI workloads on Postgres

Library for generating vector embeddings, reranking in Rust

Fast, streaming indexing and query library for AI (RAG) applications, written in Rust

Open source alternative to Perplexity AI with ability to run locally

Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.

A RAG API server written in Rust following OpenAI specs

Shinkai is a two click install AI manager (Ollama compatible for Windows, Mac and Linux). It lets you download/use AI models, RAG, and performs actions for you with tooling (very soon).

Fluent CLI is an advanced command-line interface designed to interact seamlessly with multiple workflow systems like FlowiseAI, Langflow, Make, and Zapier. Tailored for developers and IT professionals, Fluent CLI facilitates robust automation, simplifies complex interactions, and enhances productivity through a powerful and command suite

To implement LLM as a services.

Manage and chat with your bookmarks.

graph + ai in your products; reduce costs and get correct answers from your data

A terminal based interactive agent for working with multi-turn llms

A project written in the Rust language with the goal of offline load of small LLM Model, specifically RAG (Retrieval Augmented Generation) on mobile devices.

A statically typed framework for working with LLMs

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

A library to gather structured statistics on the source code files in a software repository, generate embeddings and store in a vector database.