Open-source alternatives to Slime

rllm is an asynchronous reinforcement learning framework for training language agents. It provides a unified pipeline that runs the same agent code for both evaluation and training, automatically capturing traces for gradient computation. The framework supports distributed reinforcement learning across multiple GPUs and nodes using pluggable backends, and executes agents in isolated sandboxes—either locally or in the cloud—for safe and scalable rollout collection. It trains agents built with LangGraph, SmolAgents, OpenAI Agents SDK, or custom frameworks without requiring core logic changes. T

mmagic is a multimodal training pipeline and framework for generative AI, focusing on visual synthesis and restoration. It provides the infrastructure to build and train models for tasks such as text-to-image and text-to-video generation, 3D-aware content synthesis, and high-fidelity image translation using diffusion models and generative adversarial networks. The project distinguishes itself through specialized capabilities for generative model personalization, including techniques for fine-tuning subjects and styles. It also supports advanced visual manipulations such as latent space interp

Baselines is a comprehensive suite of frameworks for reinforcement learning algorithm implementation, imitation learning, and training orchestration. It provides a library of standardized learning algorithms used to benchmark and replicate research results, alongside a deep learning policy framework for constructing neural network architectures such as multi-layer perceptrons, convolutional networks, and long short-term memory networks. The project includes a specialized imitation learning toolkit that enables agents to mimic expert behavior through behavior cloning and generative adversarial

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

Isaac Lab is an open-source framework for training robot policies in physically simulated environments, supporting both single-agent and multi-agent reinforcement learning. It is built on an Omniverse-PhysX simulation backend that models rigid bodies, articulated systems, deformable objects, and sensors, and provides a task-based environment configuration system where each training environment is defined as a modular class specifying observation spaces, action spaces, reward functions, and termination conditions. The framework distinguishes itself through an RL-library abstraction layer that

llm-foundry is a training framework for large language models, providing a system for foundation model pre-training and supervised fine-tuning. It includes a distributed trainer for scaling workloads across multiple nodes and GPUs, a dataset streaming pipeline for loading data from cloud storage, and a parameter-efficient fine-tuning implementation. The framework distinguishes itself through its use of parameter sharding and high-throughput data streaming to maintain stability during large-scale training. It incorporates low-rank adaptation to reduce computational costs and uses eight-bit flo

Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

This project is an LLM research orchestrator and autonomous AI agent framework designed to automate the scientific lifecycle. It functions as an end-to-end research pipeline and model training toolkit, managing everything from initial literature reviews and hypothesis testing to the final drafting of academic papers. The system is distinguished by its ability to convert unstructured academic PDFs into machine-executable knowledge layers, allowing agents to reproduce and extend research findings. It employs a two-loop orchestration architecture and a specialized research engineering skill libr

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

This is a structured deep learning curriculum for programmers, delivered as a collection of Jupyter notebooks. It teaches the fundamentals of training neural networks for computer vision, natural language processing, tabular data analysis, and collaborative filtering using PyTorch and the fastai library. The course is designed to be hands-on, guiding learners from building a training loop from scratch to fine-tuning pretrained models for a variety of practical tasks. The curriculum distinguishes itself by covering the full lifecycle of a deep learning project, from data preparation and augmen

This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

This project provides a comprehensive technical guide and framework for engineering large-scale machine learning systems. It covers the full lifecycle of model development, focusing on the infrastructure and computational principles required to build, train, and serve generative AI models across distributed GPU clusters. The repository distinguishes itself by offering deep-dive tutorials and implementation strategies for complex system challenges. It emphasizes high-performance architectural primitives, such as collective communication orchestration, distributed tensor sharding, and static gr

This project is a singing voice conversion tool based on VITS generative modeling. It transforms the identity of a singing voice to a target speaker while preserving the original melody, lyrics, and intonation. The system distinguishes itself through hybrid voice synthesis, allowing for the blending of multiple speaker identities via linear model interpolation. It utilizes cluster-based feature retrieval to increase target voice similarity and employs a diffusion probabilistic model as a post-processor to remove electronic artifacts and improve vocal clarity. The software covers a broad rang

This is a PyTorch reinforcement learning library designed for training agents in simulation environments. It provides a collection of deep reinforcement learning algorithms focusing on policy gradient methods and trust-region optimization. The library implements a suite of policy gradient algorithms, including A2C and PPO, alongside a framework for imitation learning using Generative Adversarial Imitation Learning. It specifically features a scalable implementation of the ACKTR algorithm, utilizing Kronecker-factored approximations to enable efficient trust-region optimization. The codebase

This project is a comprehensive deep reinforcement learning course and training platform. It provides a structured educational curriculum that combines theoretical lessons with hands-on tutorials to teach the implementation of neural networks and agent behavior. The platform integrates a model sharing hub where users can upload, download, and version trained machine learning models. It also features a benchmarking system that uses leaderboards to evaluate and compare agent performance against community standards. The educational experience is delivered through interactive notebooks and inclu

Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge

Mooncake is a disaggregated large language model serving platform and distributed key-value store designed for high-performance inference infrastructure. It functions as a GPU memory orchestrator and KV cache management system that pools and transfers key-value caches across clusters to accelerate inference. The system distinguishes itself by separating the prefill and decode phases of inference into distinct hardware clusters to optimize resource utilization. It utilizes a high-performance RDMA distributed cache with zero-copy transfers to move data between compute nodes, bypassing the CPU t

This project is a transformer post-training toolkit and reinforcement learning library designed to align language model behavior with human preferences. It provides a framework for managing the transition from supervised fine-tuning to reinforcement learning and preference optimization. The library distinguishes itself through a specialized focus on preference optimization and reward modeling, enabling the adjustment of model outputs based on preferred versus rejected examples. It also includes capabilities for training agents within controlled sandbox environments using task suites and verif

Dynamo is a distributed inference orchestration platform designed for large language models. It functions as a system to coordinate prefill and decode phases across GPU nodes, utilizing a multi-backend runtime adapter to connect engines like vLLM and TensorRT-LLM through a unified block-oriented memory interface. An OpenAI-compatible API server provides the frontend for integration with existing tools and clients. The project is distinguished by its disaggregated serving architecture, which separates prompt processing and token generation onto independent GPU pools to optimize throughput and

This project is a collection of pretrained reinforcement learning agents and training scripts built on Stable Baselines3 and Gymnasium. It provides a framework for training agents to solve specific tasks, managing experiment reproducibility, and deploying pretrained models. The system includes a specialized benchmarking suite and optimization tools for tuning agent settings. It utilizes automated search spaces and distributed trials to maximize performance, while employing bootstrap sampling to generate statistically robust performance metrics and confidence intervals. Broad capabilities cov

LMCache is a distributed key-value cache manager and tiering system designed to accelerate large language model inference. It functions as a tiered storage layer that offloads tensors from GPU memory to CPU RAM, local disks, or remote object stores, enabling the reuse of cached prefixes across different inference sessions and serving engines. The system differentiates itself through a disaggregated prefill-decode model, which separates prompt processing from token generation by transferring caches between distributed compute nodes. It utilizes peer-to-peer orchestration to share and retrieve

DataFlow is an agent-based workflow orchestrator and data pipeline designed to synthesize, clean, and augment large-scale datasets for training large language models. It functions as a synthetic data generator and text curation tool, utilizing an intelligent assistant to assemble modular processing operators into functional pipelines based on user requirements. The project distinguishes itself through a low-code approach, providing a web-based visual interface for designing and monitoring multi-stage execution flows. It features an operator-based registry system that allows for the integratio

AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a framework for developing multi-turn reasoning agents and training large models using reinforcement learning from human feedback. The project implements a toolkit for improving the visual reasoning and geometry problem solving capabilities of vision-language models. It utilizes a memory-efficient tuning system to optimize mathematical and reasoning models across different inference backends. The infrastructure supports large-scale training through tensor, pipeline, and expert p