Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation

An agent benchmark with tasks in a simulated software company.

An AI-powered interactive avatar engine using Live2D, LLM, ASR, TTS, and RVC. Ideal for VTubing, streaming, and virtual assistant applications.

Theme your iPod nano 7th and 6th generation with custom icons, wallpapers, clock faces, change or hide labels, apply custom font, and more.

Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

Our library for RL environments + evals

Automate browser based workflows with AI

Plug-and-play tree search for agents

📃 A better UX for chat, writing content, and coding with LLMs.

screenpipe turns your computer into a personal AI that knows everything you've done. record. search. automate. all local, all private, all yours.

smol models are fun too

Entropy Based Sampling and Parallel CoT Decoding

Official repository for ORPO

Optimizing inference proxy for LLMs

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Vane is an AI-powered answering engine.

Contains the prompts we use to talk to various LLMs for different utilities inside the editor

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

Kernel Extension allows to pin thread on a certain cpu core on Apple Silicon machines

Kernel extension that enables TSO for Apple silicon processes

CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.

[NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

A multimedia sketchpad

AICI: Prompts as (Wasm) Programs

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

Large Action Model framework to develop AI Web Agents

Beyond Language Models: Byte Models are Digital World Simulators