Reinforcement Learning: open-source projects on GitHub
51 repositories on Reinforcement Learning, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
Web UI for Model Training
A simple web interface to train and run open language models (Gemma 4, Qwen3.6, DeepSeek, GPT‑OSS) locally, leveraging efficient fine‑tuning techniques.
★ 64,107 · PythonDeep Understanding AI Agent
Open repository of the book 'Deep Understanding AI Agent': full text, compiled PDF, and code for each section.
★ 58,104 · PythonRay: AI Compute Engine
Ray is a distributed engine for AI computing, combining a runtime core and a set of libraries to accelerate ML workloads.
★ 42,516 · PythonSGLang: LLM Framework
SGLang is a high-performance framework for serving large language and multimodal models.
★ 27,854 · PythonOPEN-SOURCE FINANCIAL LLMS FOR DATA ANALYSIS
FinGPT is a suite of open-source financial large language models from AI4Finance Foundation. The project offers lightweight fine-tuning (under $300) instead of full train
★ 21,591 · Jupyter NotebookAGENT-LIGHTNING - TRAIN AI AGENTS
Platform for fast training and deployment of AI agents in Python. Enables faster creation of intelligent assistants.
★ 18,957 · PythonROBUST RL ON PYTORCH
PyTorch version of Stable Baselines with verified implementations of reinforcement learning algorithms. 13.4K stars on GitHub.
★ 14,015 · PythonOUMI EASY LLM TUNING
OUMI lets you quickly fine‑tune (SFT/RL), evaluate, and deploy Qwen, Gemma, and any open agentic LLM/VLM without extra complexity.
★ 9,433 · PythonAI engineering from scratch
Learn, build it, and deliver it to others.
★ 7,884 · PythonVLM-R1: Smart Image Recognition
The project demonstrates how reinforcement learning improves image understanding by multimedia models.
★ 6,046 · PythonLLM FROM SCRATCH IN PYTORCH
The reasoning-from-scratch project shows how to build a Reasoning LLM from scratch in PyTorch, step by step. Implemented in Jupyter notebooks: architecture, training with
★ 5,831 · Jupyter NotebookRL INFRASTRUCTURE FOR EMBODIED AND AGENTIC AI
Scalable reinforcement learning infrastructure for robotic and agentic systems. Supports real robots, simulators, and VLA models with distributed rollout.
★ 5,666 · PythonEASYR1: MULTIMODAL RL TRAINING
EasyR1 is a scalable framework for multimodal reinforcement learning training on veRL, delivering high efficiency and ease of use.
★ 5,215 · PythonSmart Agents with RL
AReaL — a bridge between reinforcement learning and LLM agents. Simple and flexible.
★ 5,177 · PythonXTUNER: TRAINER FOR LARGE MoE
A Next-Generation Training Engine Built for Ultra-Large MoE Models. ⭐ 5138 stars on GitHub!
★ 5,138 · PythonMetaClaw: learning agent
MetaClaw is a simple way to talk to an AI agent that learns on the fly during conversation and continuously improves its behavior. Written in Python, it has a modular str
★ 3,370 · PythonSKYWORK-R1V VISION LANGUAGE AI
The Skywork-R1V model series combines vision and language for complex reasoning. Available in Python and already has over 3k stars.
★ 3,173 · Pythonrl-baselines3-zoo - RL Training with Hyperparameters
Framework for training Stable Baselines3 agents with automatic hyperparameter tuning and ready pre-trained models.
★ 2,912 · PythonOSWorld: BENCHMARK FOR AI AGENTS
OSWorld is a benchmark for evaluating multimodal AI agents in real computer environments. Open tasks in real operating systems.
★ 2,911 · PythonFORMAL VERIFICATION OF AI AGENTS
Enterprise agent library with formal verification in Lean. 2850★. Open alternative to costly YC startups. FastAPI + Bayesian inference.
★ 2,897 · PythonNVIDIA NEMOTRON: TRAINING RECIPES AND DEPLOYMENT
NVIDIA repository with training recipes, deployment guides, and usage examples for Nemotron models. Supports multimodal agents with up to 1M token context.
★ 2,361 · Jupyter NotebookMAGE: AI AGENT FOR PC CONTROL
Microsoft released Mage — an agent for GUI control via flow matching. The model edits images and performs computer tasks without fine-tuning.
★ 1,782 · PythonAgent Apprenticeship - Teaching AI
The project creates a living ecosystem where AI agents learn on real tasks through iterative cycles and exchange of training signals.
★ 1,605JUDGEVAL STACK FOR AGENTS
Platform for continuous improvement of AI agents: collecting environment data and evaluations for monitoring and growth.
★ 1,036 · PythonAgileRL - Evolutionary Acceleration
AgileRL speeds up RL training 10× via evolutionary hyperparameter optimization and ready-to-use SOTA algorithms.
★ 967 · PythonGYM - Model Evaluation
Helps evaluate and improve LLMs through environments and agents with feedback and testing.
★ 932 · PythonCurated Computer-Use Agent Resources
Open catalog of computer-use agents with reviewed papers, GUI models, datasets, benchmarks, and tools. Includes reusable JSONL and SQLite data.
★ 880 · PythonMOBILEGYM: ANDROID AGENT TRAINING
MobileGym is a browser‑hosted Android emulator for research on mobile GUI agents. The platform provides verifiable evaluation and highly parallel online reinforcement‑lea
★ 866 · PythonHALO: FRAMEWORK FOR LLM TRAINING
Halo is an open-source framework from White Circle for training large language and multimodal models. It supports agent-based training, async-RL, distributed training, an
★ 862 · PythonTURN ANY REPO INTO RL ENV
Repo2RLEnv turns any GitHub repository into a verifiable RL environment for coding agents. Harbour tasks prepare, evaluate, and publish to Hugging Face Hub. 739 stars, Py
★ 787 · PythonSTABLE-BASELINES3-CONTRIB: NEW RL ALGORITHMS
The contrib package for Stable-Baselines3 contains experimental reinforcement learning algorithms. It includes GSDE implementations, Gym environment support, and PyTorch
★ 746 · PythonOVERVIEW OF VISUAL-LANGUAGE MODELS
A collection of reviews and links to articles on vision-language models, constantly updated on GitHub.
★ 733 · HTMLRELAX: ASYNCHRONOUS RL FOR MULTIMODAL POST‑TRAINING
Relax — an asynchronous reinforcement learning engine for scalable post‑training agents. It supports efficient distributed training, multi-agent scenarios, and working wi
★ 676 · PythonFINENVS: RL-ENVIRONMENTS OF THE NEXT GENERATION
FineEnvs — Python library for creating and scaling reinforcement learning environments with LLM capabilities. It simplifies LLM-agent integration, supports training via G
★ 563 · PythonOPEN-AGENTRL - UNIVERSAL AGENT RL
Open-AgentRL offers RLAnything and DemyAgent — general and scalable agent RL algorithms for terminal, GUI, SWE, and tool use.
★ 545 · PythonABC-GRPO: ALL-QUADRANT BOUNDING MODEL
ABC-GRPO implements all-quadrant bounded clipping for GRPO, improving LLM training stability. Code based on arXiv:2601.03895, written in Python. Project has 442 GitHub st
★ 438 · PythonAgent Environment Framework
Framework for building realistic reinforcement learning environments with collaboration tools for researchers and engineers.
★ 438 · PythonTORCHTRADE - AI TRADING WITHOUT BORDERS
A modular reinforcement learning framework for creating and testing algorithmic trading strategies in Python.
★ 428 · PythonARENO: Accelerate RL Single Node
ARENO simplifies scaling post-training RL on a single node, delivering high speed with minimal setup.
★ 389 · PythonVERL-OMNI: REINFORCEMENT LEARNING
Framework for RL training of diffusion and multimodal models. 347 stars on GitHub.
★ 347 · PythonHUD-Python RL Evaluation
An OSS environment for RL with ready‑to‑use agent evaluation tools. Run, configure, and get results.
★ 329 · PythonAGI ALPHA AGENT V0
AGI‑Alpha‑Agent‑v0:Python meta‑agentic AGI framework. Implements Identify → Out‑Learn → Out‑Think → Out‑Design → Out‑Strategise → Out‑Execute. 292 stars GitHub today AI M
★ 310 · PythonAESTHETIC HTML/CSS GENERATION FROM PROMPTS
AesCode turns prompts into editable HTML/CSS infographics. Uses image generators as aesthetic guidance and cross-modal rewards with RL (Qwen3) for verifiable code. 225★ o
★ 281 · PythonBUILD YOUR AI INTRANET
Autonomous grid unites your computers into a single infrastructure for running AI models: training, fine‑tuning and inference. Supports distributed computing, fine‑tuning
★ 278 · PythonCURATED LIST OF OPD RESOURCES
A collection of papers, frameworks, and tools for on‑policy distillation of large language models. Ideal for LLM researchers and engineers.
★ 277FREE ML COURSES FROM TOP UNIVERSITIES
Collection of free machine‑learning courses from MIT, Stanford, Berkeley, CMU, NYU and UChicago. All lectures and yearly editions gathered on one searchable page.
★ 254 · AstroComprehensive AI Engineering Course
Free 173-lesson course covering data, ML, deep learning, and AI engineering with 166 runnable labs. Covers math, code, systems, and security under CC BY-NC 4.0.
★ 175 · PythonAgentic RL Tutorial & Benchmark
33-chapter Chinese tutorial from RL concepts to GRPO with TRL examples, plus reproducible discriminative-model benchmark comparing encoder, LLM-LoRA, and rule baselines.
★ 146 · PythonSystem 1 Model Framework
Framework to train, test, and serve System 1 decision models on language and multimodal platforms.
★ 137 · PythonHands-On LLM Full-Stack Course
Comprehensive tutorial implementing LLMs from scratch: builds Transformer in PyTorch, reproduces Pretrain/SFT/LoRA/DPO/GRPO on single GPU, covers PEFT/Agent/RAG with real
★ 124 · PythonUniRL: Multimodal Learning
UniRL is a Python framework for unified reinforcement learning of multimedia models. It enables joint training of vision, language, and audio in a single RL cycle.
★ 60 · PythonNew projects on this topic in Telegram
Telegram →