ai-backend

Build, run and scale AI agents like API and microservices

Run Hermes Agent free 24/7 on GitHub Codespaces + Tailscale VPN. Step-by-step guide in English 🇬🇧 and Vietnamese 🇻🇳

Your machine's AI brain. One 20MB binary gives every tool, script, and cron job shared AI memory + 136 API endpoints. 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

The open-source, self-hosted backend for agent-built, agent-powered SaaS—auth, Postgres, AI runtime, sandbox, browser, jobs, billing, security, and observability in one stack.

A modular FastAPI backend for document ingestion, FAISS-based semantic search, and Retrieval-Augmented Generation using OpenAI-compatible models.

Manifest Backend-as-a-Service Docs

👉 A production-oriented FastAPI backend for LLM generation, structured AI output, token usage, cost estimation, and provider error handling.

Privacy-first local LLM platform built with Java 21, Spring AI, Ollama, and MongoDB for secure document processing and conversational AI.

Creative portfolio site for Ali Eslah, AI Backend Engineer.

Realtime voice AI backend with low-latency streaming using WebSockets

Custos - Intelligent LLM Gateway with smart routing, caching, and cost governance

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.

The Text2Pen Backend

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.

Scalable GenAI-powered system to extract structured invoice data from PDFs & images, detect errors, and process large batches efficiently.

FastAPI is a high-performance web framework used for building APIs with Python. It is built on modern Python standards, specifically utilizing Starlette for the web parts and Pydantic for data validation and serialization.

Machine learning models for predicting type 1 diabetes complications — retinopathy, nephropathy, neuropathy, diabetic foot (Python, scikit-learn, XGBoost)