Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and identity-aware from day one.

Your machine's AI brain. One 20MB binary gives every tool, script, and cron job shared AI memory + 114 API routes. Desktop app, CLI, Telegram — all connected. Rust-powered.

A powerful, faster, scalable full-stack boilerplace for AI inference using Node.js, Python, Redis, and Docker

Create your backend with AI

Manifest Backend-as-a-Service Docs

A production-ready FastAPI with Pydantic AI backend service that provides OpenAI-powered chat completions with streaming support, designed for seamless integration with the Vercel AI SDK.

Realtime voice AI backend with low-latency streaming using WebSockets

AI-powered backend for user requests, enabling seamless chatbot integration... Created at https://coslynx.com

A clean, minimal RAG backend that demonstrates document ingestion, embedding, retrieval, and LLM-based answering with persistent local storage.

Módulo de inteligencia artificial para dabetai. Modelos de predicción de complicaciones diabéticas tipo 1 (retinopatía, nefropatía, neuropatía, pie diabético). Componente de backend para plataforma de monitoreo de la diabetes.

FastAPI-based stateless inference service untuk serving multiple AI models with input video.

Enterprise RAG backend for knowledge retrieval using FastAPI, PostgreSQL/pgvector, AWS S3, and AWS Bedrock.

Backend-controlled AI feedback agent with memory, state guards, and safe tool execution.

Production-pattern backend service integrating LLM inference and vector similarity search with FastAPI, OpenAI, and ChromaDB

AI-powered quotation intelligence microservice leveraging FastAPI, Pydantic schema enforcement, decimal-accurate pricing and tax computation, and bilingual (EN/AR) AI-driven email generation via an LLM abstraction layer. Features OpenAPI contracts, pytest-based CI validation, and Dockerized, cloud-native deployment for scalable CRM and sales automa

Node.js backend API for a video transcription prompt application. Built with Fastify, Prisma, Zod, and TypeScript. Supports MP3 video uploads, custom prompts with {transcription} placeholders, and streaming AI completions (e.g., via OpenAI) for interactive video content querying and generation.

A simple Node.js API that uses Google Gemini to generate responses from text, images, documents, or audio files. Supports file uploads via multipart/form-data and returns AI-generated content.

Simplified API for OpenAI requests, providing basic access and response handling... Created at https://coslynx.com

Production-ready Node.js REST API boilerplate with Express, route organization, auth middleware, and error handling — built for AI automation backends

Production-ready Retrieval-Augmented Generation (RAG) backend system with Pinecone, Groq, Docker & MLflow observability.