Aquiles-ai

A high-performance, memory-efficient inference server for diffusion models (image/video generation), compatible with the OpenAI client

Building a Multimodal Model with LFM2.5 and Kimi-K2.6

Drop-in sandbox component that executes AI-generated React code with zero configuration.

Drop-in sandbox to test AI-generated React components against any OpenAI-compatible LLM endpoint. No backend, no config — connect your own model, describe a component, and watch it render live.

Understanding the Pipeline for Training an LLM from Scratch

AI SDK - Aquiles-ai Provider

Extensible framework for creating and managing LLM function calling.

Is a high-performance Augmented Recovery-Generation (RAG) solution based on Redis, Qdrant or PostgreSQL. It offers a high-level interface using FastAPI REST APIs