llm

The agent that remembers and learns.

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

Recipes to train reward model for RLHF.

AgentEvolver: Towards Efficient Self-Evolving Agent System

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Data and tools for generating and inspecting OLMo pre-training data.

Nvidia GPU exporter for prometheus using nvidia-smi binary OR using NVML

OpenSource Production ready Customer service with built in Evals and monitoring

Cache-Augmented Generation: A Simple, Efficient Alternative to RAG

AI Browser Automation

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.

Build AI WhatsApp Bots with Pure Python

Learn LLM internals step by step - from tokenization to attention to inference optimization.

The LLM Anti-Framework

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

LLM Prompt Injection Detector

A RAG LLM co-pilot for browsing the web, powered by local LLMs