The agent that grows with you

Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase

The fastest way to create an HTML app

Mobile Shell

LLM inference in C/C++

This repo is dedicated to providing open-source tutorials for Large Language Model experimentation.

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

build-once run-anywhere c library

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

Structured Outputs

structured outputs for llms

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Curate better data for LLMs

Wheels for llama-cpp-python compiled with cuBLAS support

AI chat for any model.

A new bootable USB solution.

LLM plugin for running models using llama.cpp

Access large language models from the command-line

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Chat language model that can use tools and interpret the results

A guidance compatibility layer for llama-cpp-python

Stream your reMarkable screen to any browser - no hacks, no dependencies, just install and go

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …

A truly Open Source MongoDB alternative

LLM-based code completion engine

nanobind: tiny and efficient C++/Python bindings

Generate python stub files for code completion in IDEs for nanobind modules.

An open source ChatGPT UI.

Let's make sand talk

Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.