Home

Network ML

A simple, modern C++ library for REST API requests and LLM chat (local via Ollama, or cloud providers), built on libcurl.

#include "networkml.h"

ML::Requests req;
ML::Response r = req.get("https://api.example.com/data");
if (r.ok()) std::cout << r.status << "\n" << r.body;

ML::Chat chat(Provider::Ollama, "llama3.2:1b");
std::cout << chat.ask("Explain RAII in one sentence.");

Documentation

• Getting Started: requirements, building with CMake + vcpkg, prebuilt binaries
• Requests: the HTTP client (verbs, Response, auth, downloads, uploads, retries)
• Chat: the LLM client (providers, streaming, reasoning, history)

ML::File moved to File ML in v2.1.

Features at a glance

• HTTP verbs get / post / put / patch / del / head, each returning a rich Response (status, body, response headers)
• Auth helpers, URL encoding, file download/upload, and opt-in retries with backoff
• Chat across Ollama, Groq, OpenRouter, DeepSeek, OpenAI, Anthropic behind one API
• Token streaming, reasoning-token support, conversation memory, save/load history
• Built on statically-linked libcurl (HTTPS via Schannel on Windows), C++17