
oat
🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.
Stars: 264

Oat is a simple and efficient framework for running online LLM alignment algorithms. It implements a distributed Actor-Learner-Oracle architecture, with components optimized using state-of-the-art tools. Oat simplifies the experimental pipeline of LLM alignment by serving an Oracle online for preference data labeling and model evaluation. It provides a variety of oracles for simulating feedback and supports verifiable rewards. Oat's modular structure allows for easy inheritance and modification of classes, enabling rapid prototyping and experimentation with new algorithms. The framework implements cutting-edge online algorithms like PPO for math reasoning and various online exploration algorithms.
README:
Installation | Usage | Examples | Benchmarking | Citation
- 21/03/2025: We incorporate Dr. GRPO, which fixes the optimization bias in GRPO.
- 26/01/2025: We support reinforcement learning with verifiable rewards (RLVR) for math reasoning.
- A quick example of R1-Zero-like training with GRPO.
- 20/10/2024: We open source Oat, an online LLM alignment framework developed during a research project on online LLM exploration (sample-efficient alignment).
Oat 🌾 is a simple yet efficient framework for running online LLM alignment algorithms. Its key features include:
- High Efficiency: Oat implements a distributed Actor-Learner-Oracle architecture, with each component being optimized using state-of-the-art tools:
-
Simplified Workflow: Oat simplifies the experimental pipeline of LLM alignment. With an
Oracle
served online, we can flexibly query it for preference data labeling as well as anytime model evaluation. All you need is to launch experiments and monitor real-time learning curves (e.g., win rate) on wandb (see reproduced results) — no need for manual training, checkpointing and loading for evaluation. -
Oracle Simulation: Oat provides a diverse set of oracles to simulate preference/reward/verification feedback.
- Verifiable rewards supported using rule-based functions.
- Lightweight reward models run within the actor's process, enabling quick testing on as few as two GPUs.
- Larger and more capable reward models can be served remotely, harnessing additional compute and memory resources.
- LLM-as-a-judge is supported via querying OpenAI API for model-based pairwise ranking.
- Ease of Use: Oat's modular structure allows researchers to easily inherit and modify existing classes, enabling rapid prototyping and experimentation with new algorithms.
-
Cutting-Edge Algorithms: Oat implements state-of-the-art online algorithms, fostering innovation and fair benchmarking.
- PPO/Dr.GRPO (online RL) for math reasoning.
- Online DPO/SimPO/IPO for online preference learning.
- Online exploration (active alignment) algorithms, including SEA, APL and XPO.
In a python environment with supported versions (we recommend 3.10
), you could install oat via PyPI:
pip install vllm==0.7.2 && pip install oat-llm
Or you could also install in "editable" mode for local development:
git clone [email protected]:sail-sg/oat.git
cd oat
pip install vllm==0.7.2 && pip install -e .
The benchmarking compares oat with the online DPO implementation from huggingface/trl. Below, we outline the configurations used for oat and present the benchmarking results. Notably, oat 🌾 achieves up to 2.5x computational efficiency compared to trl 🤗.
Please refer to Appendix C of our paper for a detailed discussion of the benchmarking methods and results.
If you find this codebase useful for your research, please consider citing:
LLM online alignment framework:
@misc{
liu2025oat,
title={OAT: A research-friendly framework for LLM online alignment},
author={Zichen Liu and Changyu Chen and Chao Du and Wee Sun Lee and Min Lin},
howpublished={\url{https://github.com/sail-sg/oat}},
year={2025}
}
Online exploration method:
@article{
liu2024sea,
title={Sample-Efficient Alignment for LLMs},
author={Zichen Liu and Changyu Chen and Chao Du and Wee Sun Lee and Min Lin},
journal={arXiv preprint arXiv:2411.01493},
year={2024}
}
oat
is distributed under the terms of the Apache2 license.
We thank the following awesome projects that have contributed to the development of oat:
This is not an official Sea Limited or Garena Online Private Limited product.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for oat
Similar Open Source Tools

oat
Oat is a simple and efficient framework for running online LLM alignment algorithms. It implements a distributed Actor-Learner-Oracle architecture, with components optimized using state-of-the-art tools. Oat simplifies the experimental pipeline of LLM alignment by serving an Oracle online for preference data labeling and model evaluation. It provides a variety of oracles for simulating feedback and supports verifiable rewards. Oat's modular structure allows for easy inheritance and modification of classes, enabling rapid prototyping and experimentation with new algorithms. The framework implements cutting-edge online algorithms like PPO for math reasoning and various online exploration algorithms.

neuro-san-studio
Neuro SAN Studio is an open-source library for building agent networks across various industries. It simplifies the development of collaborative AI systems by enabling users to create sophisticated multi-agent applications using declarative configuration files. The tool offers features like data-driven configuration, adaptive communication protocols, safe data handling, dynamic agent network designer, flexible tool integration, robust traceability, and cloud-agnostic deployment. It has been used in various use-cases such as automated generation of multi-agent configurations, airline policy assistance, banking operations, market analysis in consumer packaged goods, insurance claims processing, intranet knowledge management, retail operations, telco network support, therapy vignette supervision, and more.

Genesis
Genesis is a physics platform designed for general purpose Robotics/Embodied AI/Physical AI applications. It includes a universal physics engine, a lightweight, ultra-fast, pythonic, and user-friendly robotics simulation platform, a powerful and fast photo-realistic rendering system, and a generative data engine that transforms user-prompted natural language description into various modalities of data. It aims to lower the barrier to using physics simulations, unify state-of-the-art physics solvers, and minimize human effort in collecting and generating data for robotics and other domains.

raga-llm-hub
Raga LLM Hub is a comprehensive evaluation toolkit for Language and Learning Models (LLMs) with over 100 meticulously designed metrics. It allows developers and organizations to evaluate and compare LLMs effectively, establishing guardrails for LLMs and Retrieval Augmented Generation (RAG) applications. The platform assesses aspects like Relevance & Understanding, Content Quality, Hallucination, Safety & Bias, Context Relevance, Guardrails, and Vulnerability scanning, along with Metric-Based Tests for quantitative analysis. It helps teams identify and fix issues throughout the LLM lifecycle, revolutionizing reliability and trustworthiness.

LLM-Zero-to-Hundred
LLM-Zero-to-Hundred is a repository showcasing various applications of LLM chatbots and providing insights into training and fine-tuning Language Models. It includes projects like WebGPT, RAG-GPT, WebRAGQuery, LLM Full Finetuning, RAG-Master LLamaindex vs Langchain, open-source-RAG-GEMMA, and HUMAIN: Advanced Multimodal, Multitask Chatbot. The projects cover features like ChatGPT-like interaction, RAG capabilities, image generation and understanding, DuckDuckGo integration, summarization, text and voice interaction, and memory access. Tutorials include LLM Function Calling and Visualizing Text Vectorization. The projects have a general structure with folders for README, HELPER, .env, configs, data, src, images, and utils.

Mooncake
Mooncake is a serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates prefill and decoding clusters, leveraging underutilized CPU, DRAM, and SSD resources of the GPU cluster. Mooncake's scheduler balances throughput and latency-related SLOs, with a prediction-based early rejection policy for highly overloaded scenarios. It excels in long-context scenarios, achieving up to a 525% increase in throughput while handling 75% more requests under real workloads.

HuixiangDou2
HuixiangDou2 is a robustly optimized GraphRAG approach that integrates multiple open-source projects to improve performance in graph-based augmented generation. It conducts comparative experiments and achieves a significant score increase, leading to a GraphRAG implementation with recognized performance. The repository provides code improvements, dense retrieval for querying entities and relationships, real domain knowledge testing, and impact analysis on accuracy.

aistore
AIStore is a lightweight object storage system designed for AI applications. It is highly scalable, reliable, and easy to use. AIStore can be deployed on any commodity hardware, and it can be used to store and manage large datasets for deep learning and other AI applications.

openvino
OpenVINOâ„¢ is an open-source toolkit for optimizing and deploying AI inference. It provides a common API to deliver inference solutions on various platforms, including CPU, GPU, NPU, and heterogeneous devices. OpenVINOâ„¢ supports pre-trained models from Open Model Zoo and popular frameworks like TensorFlow, PyTorch, and ONNX. Key components of OpenVINOâ„¢ include the OpenVINOâ„¢ Runtime, plugins for different hardware devices, frontends for reading models from native framework formats, and the OpenVINO Model Converter (OVC) for adjusting models for optimal execution on target devices.

CogVideo
CogVideo is an open-source repository that provides pretrained text-to-video models for generating videos based on input text. It includes models like CogVideoX-2B and CogVideo, offering powerful video generation capabilities. The repository offers tools for inference, fine-tuning, and model conversion, along with demos showcasing the model's capabilities through CLI, web UI, and online experiences. CogVideo aims to facilitate the creation of high-quality videos from textual descriptions, catering to a wide range of applications.

poml
POML (Prompt Orchestration Markup Language) is a novel markup language designed to bring structure, maintainability, and versatility to advanced prompt engineering for Large Language Models (LLMs). It addresses common challenges in prompt development, such as lack of structure, complex data integration, format sensitivity, and inadequate tooling. POML provides a systematic way to organize prompt components, integrate diverse data types seamlessly, and manage presentation variations, empowering developers to create more sophisticated and reliable LLM applications.

nixtla
Nixtla is a production-ready generative pretrained transformer for time series forecasting and anomaly detection. It can accurately predict various domains such as retail, electricity, finance, and IoT with just a few lines of code. TimeGPT introduces a paradigm shift with its standout performance, efficiency, and simplicity, making it accessible even to users with minimal coding experience. The model is based on self-attention and is independently trained on a vast time series dataset to minimize forecasting error. It offers features like zero-shot inference, fine-tuning, API access, adding exogenous variables, multiple series forecasting, custom loss function, cross-validation, prediction intervals, and handling irregular timestamps.

gptme
GPTMe is a tool that allows users to interact with an LLM assistant directly in their terminal in a chat-style interface. The tool provides features for the assistant to run shell commands, execute code, read/write files, and more, making it suitable for various development and terminal-based tasks. It serves as a local alternative to ChatGPT's 'Code Interpreter,' offering flexibility and privacy when using a local model. GPTMe supports code execution, file manipulation, context passing, self-correction, and works with various AI models like GPT-4. It also includes a GitHub Bot for requesting changes and operates entirely in GitHub Actions. In progress features include handling long contexts intelligently, a web UI and API for conversations, web and desktop vision, and a tree-based conversation structure.

dash-infer
DashInfer is a C++ runtime tool designed to deliver production-level implementations highly optimized for various hardware architectures, including x86 and ARMv9. It supports Continuous Batching and NUMA-Aware capabilities for CPU, and can fully utilize modern server-grade CPUs to host large language models (LLMs) up to 14B in size. With lightweight architecture, high precision, support for mainstream open-source LLMs, post-training quantization, optimized computation kernels, NUMA-aware design, and multi-language API interfaces, DashInfer provides a versatile solution for efficient inference tasks. It supports x86 CPUs with AVX2 instruction set and ARMv9 CPUs with SVE instruction set, along with various data types like FP32, BF16, and InstantQuant. DashInfer also offers single-NUMA and multi-NUMA architectures for model inference, with detailed performance tests and inference accuracy evaluations available. The tool is supported on mainstream Linux server operating systems and provides documentation and examples for easy integration and usage.

workflows-py
LlamaIndex Workflows is a framework for orchestrating and chaining together complex systems of steps and events. It shines in orchestrating complex, multi-step processes involving AI models, APIs, and decision-making. The async-first, event-driven architecture allows building workflows that can route between different capabilities, implement parallel processing patterns, loop over complex sequences, and maintain state across multiple steps. Key features include async-first design, event-driven structure, state management, and observability through tools like Arize Phoenix and OpenTelemetry.

model2vec
Model2Vec is a technique to turn any sentence transformer into a really small static model, reducing model size by 15x and making the models up to 500x faster, with a small drop in performance. It outperforms other static embedding models like GLoVe and BPEmb, is lightweight with only `numpy` as a major dependency, offers fast inference, dataset-free distillation, and is integrated into Sentence Transformers, txtai, and Chonkie. Model2Vec creates powerful models by passing a vocabulary through a sentence transformer model, reducing dimensionality using PCA, and weighting embeddings using zipf weighting. Users can distill their own models or use pre-trained models from the HuggingFace hub. Evaluation can be done using the provided evaluation package. Model2Vec is licensed under MIT.
For similar tasks

oat
Oat is a simple and efficient framework for running online LLM alignment algorithms. It implements a distributed Actor-Learner-Oracle architecture, with components optimized using state-of-the-art tools. Oat simplifies the experimental pipeline of LLM alignment by serving an Oracle online for preference data labeling and model evaluation. It provides a variety of oracles for simulating feedback and supports verifiable rewards. Oat's modular structure allows for easy inheritance and modification of classes, enabling rapid prototyping and experimentation with new algorithms. The framework implements cutting-edge online algorithms like PPO for math reasoning and various online exploration algorithms.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.