Agent frameworks & infrastructure
Models, fine-tuning & training
Models, fine-tuning and training projects handle the model layer beneath an agent: running local checkpoints, fine-tuning them, building training datasets, and running reinforcement learning. Unsloth shows the practical side, a local UI for training and running LLMs and diffusion models, while easy-dataset covers dataset creation for fine-tuning, RAG, and evaluation.
2,504 agents · most starred first
Top 100 of 2,504
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Grok open release
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
The absolute trainer to light up AI agents.
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
A straightforward method for training your LLM, from downloading data to generating text.
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Low-code framework for building custom LLMs, neural networks, and other AI models
Kimi K2 is the large language model series developed by Moonshot AI team
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
Infrastructure for continually self‑improving agents
Tools for merging pretrained large language models.
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
Democratizing Reinforcement Learning for LLMs
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
OpenClaw-RL: Train any agent simply by talking
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/
transformers pytorch safetensors llama text-generation facebook
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
A live stream development of RL tunning for LLM agents
A library of reinforcement learning components and agents
TimeGPT-2.1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
.NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C# and F#.
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
Chinese-LLaMA 1&2、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
gguf gemma4 coding code reasoning thinking
Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
✨ Build a machine learning model from a prompt
MiniMax-M2, a model built for Max coding & agentic workflows.
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
Agentic RL Training at Scale
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
transformers safetensors qwen2 text-generation code codeqwen
transformers pytorch safetensors llama text-generation facebook
SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
This is the official implementation of Multi-Agent PPO (MAPPO).
Agent harness to publish your history from Claude Code et al. as Huggingface datasets.
Fast, Sharp & Reliable Agentic Intelligence
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
用于训练中英文对话系统的语料库 Datasets for Training Chatbot System
Implementation of all RL algorithms in a simpler way
[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
transformers safetensors llama text-generation conversational en
gguf gemma4 coding agentic terminal tool-use
Train your Agent model via our easy and efficient framework
Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0
transformers safetensors qwen3_next text-generation conversational license:apache-2.0
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调,给出三元组信息抽取微调示例。
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Adala: Autonomous DAta (Labeling) Agent framework
transformers safetensors phi4mm text-generation nlp code
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
AgentTuning: Enabling Generalized Agent Abilities for LLMs
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
Official repository of Evolutionary Optimization of Model Merging Recipes
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
transformers safetensors qwen3_moe text-generation conversational arxiv:2505.09388
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
transformers safetensors qwen3_moe text-generation conversational arxiv:2505.09388
EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.
Fine-tune LLM agents with online reinforcement learning
Evolutionary Algorithm using Python, 莫烦Python 中文AI教学
transformers gguf unsloth qwen3 qwen text-generation
A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
transformers pytorch safetensors llama text-generation facebook
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support