An agentic skills framework & software development methodology that works.

A developer vanished. The clues are in the code. Only Claude Code can find them.

Python Backtesting library for trading strategies

A TTS model capable of generating ultra-realistic dialogue in one pass.

Code and datasets for "Character-LLM: A Trainable Agent for Role-Playing"

AllenAI's post-training codebase

OpenChat: Advancing Open-source Language Models with Imperfect Data

Accurate answers and instant citations for your documents.

Offline, privacy-first grammar checker. Fast, open-source, Rust-powered

NanoGPT (124M) in 90 seconds

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

Code for "Learning to Model the World with Language." ICML 2024 Oral.

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

[ECCV'24] SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic

A curated list of awesome exploration RL resources (continually updated)

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)

Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.

A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)

This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.

Gymnasium extension for DarkSouls III, Elden Ring, and other Souls games

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

PyTorch implementation of Contrastive Learning methods

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

Initiative to read research papers

Resources on various topics being worked on at IvLabs

MetaDrive: Lightweight driving simulator for everyone