Agent frameworks & infrastructure
Models, fine-tuning & training
2,504 agents · most starred first
Models, fine-tuning & training, page 2 of 26
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
Transformer models from BERT to GPT-4, environments from Hugging Face to OpenAI. Fine-tuning, training, and prompt engineering examples. A bonus section with ChatGPT, GPT-3.5-turbo, GPT-4, and DALL-E including jump starting GPT-4, speech-to-text, text-to-speech, text to image generation with DALL-E, Google Cloud AI,HuggingGPT, and more
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
Multi-Agent Reinforcement Learning with JAX
transformers safetensors qwen2 text-generation code codeqwen
The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT models (gpt-5, gpt-o*, gpt-4o, etc.). Port of OpenAI's tiktoken with additional features.
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
Multi-Agent Reinforcement Learning with JAX
Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019
Building DeepSeek R1 from Scratch
Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. Orion-14B 系列模型包括一个具有140亿参数的多语言基座大模型以及一系列相关的衍生模型,包括对话模型,长文本模型,量化模型,RAG微调模型,Agent微调模型等。
Train Models Contrastively in Pytorch
transformers safetensors qwen text-generation custom_code zh
LLM agents as your hyperparameter optimizer.
A simple OpenAI Gym environment for single and multi-agent reinforcement learning
A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes.
ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.
Framework for enhancing LLMs for RAG tasks using fine-tuning.
Repo containing code for multi-agent deep reinforcement learning (MADRL).
Hello, I pushed some python environments for Multi Agent Reinforcement Learning.
transformers safetensors qwen3_5_moe image-text-to-text qwen world-model
transformers pytorch mpt text-generation code custom_code
A research project for natural language generation, containing the official implementations by MSRA NLC team.
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
transformers safetensors deepseek_v2 text-generation conversational custom_code
transformers safetensors deepseek_v2 text-generation conversational custom_code
transformers pytorch gpt_neox text-generation en license:apache-2.0
transformers safetensors qwen3_5_moe image-text-to-text code agent
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
transformers safetensors llama text-generation llama-factory orpo
transformers safetensors qwen2 text-generation conversational en
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
transformers safetensors gguf stablelm text-generation causal-lm
transformers safetensors qwen3_5_moe image-text-to-text moe vlm
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
A PyTorch library for building deep reinforcement learning agents.
xLAM: A Family of Large Action Models to Empower AI Agent Systems
transformers pytorch baichuan text-generation custom_code zh
Autonomous GPU Kernel Generation & Optimization via Deep Agents
PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single agent and multi-agent.
AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.
transformers pytorch safetensors llama text-generation conversational
Build high-performance AI models with modular building blocks
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.
transformers safetensors cohere2_moe text-generation conversational chat
transformers safetensors qwen2 text-generation en dataset:AI-MO/NuminaMath-CoT
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
A simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly
PyTorch Agent Net: reinforcement learning toolkit for pytorch
A parallel framework for population-based multi-agent reinforcement learning.
transformers safetensors llama text-generation nvidia chatqa-1.5
PyTorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.
A project implementing various agentic RL based on the Slime post-training framework
Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)
Framework for Multi-Agent Deep Reinforcement Learning in Poker
transformers pytorch safetensors mistral text-generation LLMs
MiniMax M2.1, a SOTA model for real-world dev & agents.
🏗️ Fine-tune, build, and deploy open-source LLMs easily!
transformers pytorch safetensors llama text-generation conversational
LongCat-Flash-Chat safetensors text-generation transformers conversational custom_code
World model reinforcement learning for multi-turn VLM agents. RL for vision framework (NeurIPS 2025).
A Gym for Agentic LLMs
Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
transformers safetensors deepseek_v2 text-generation conversational custom_code
Toolkits for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.
Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.
[CVPR'25 highlight] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch
Agentic RAG R1 Framework via Reinforcement Learning
safetensors gguf qwen3_5 code threejs 3d
Learning to Communicate with Deep Multi-Agent Reinforcement Learning
An open-source implementation for training LLaVA-NeXT.
Easily train AlphaZero-like agents on any environment you want!
transformers pytorch baichuan text-generation custom_code en
a Lightweight library for sequential learning agents, including reinforcement learning
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
transformers safetensors qwen3 text-generation conversational en
Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
transformers pytorch tensorboard safetensors llama text-generation
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning
Ready-made tokenizer library for working with GPT and tiktoken
🦖 X—LLM: Cutting Edge & Easy LLM Finetuning
A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL
[EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"
An easy-to-use, fast toolkit to scale up RL post-training on a single node.
SkyText是由奇点智源发布的中文GPT3预训练大模型,可以进行文章续写、对话、中英翻译、内容风格生成、推理、诗词对联等不同任务。| SkyText is a Chinese GPT3 pre-trained large model released by Singularity-AI, which can perform different tasks such as chatting, Q&A, and Chinese-English translation.
Compile organizational policy into verifiable decision training data.
Official code for "Self-Distilled Agentic Reinforcement Learning"
siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems