WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting.

Port of Facebook's LLaMA model in C/C++

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory

Train transformer language models with reinforcement learning.

Model Context Protocol Servers

🦜🔗 Build context-aware reasoning applications

VS Code extension for local LLM-assisted code/text completion

OpenSCAD Web Playground

OpenSCAD - The Programmers Solid 3D CAD Modeller

Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…

Webassembly port of OpenSCAD

Build script for various toolchains used by KOReader

A set of scripts to synchronize a kobo reader with popular cloud services

Port of OpenAI's Whisper model in C/C++

A fast, local neural text to speech system

High-performance In-browser LLM Inference Engine

Stream data through multiple series of QR codes

AI + Data, online. https://vespa.ai

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

A SQLite extension for generate text embeddings from GGUF models using llama.cpp

Transform a Wikidata JSON dump into a DuckDB database

ai-generated apps , full stack + generative UI

Letta (fka MemGPT) is a framework for creating stateful LLM services.

A toolkit for describing model features and intervening on those features to steer behavior.

Utilities intended for use with Llama models.

Model components of the Llama Stack APIs

Agentic components of the Llama Stack APIs

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…