1.rohitg00 / ai-engineering-from-scratch
Learn AI Engineering! Learn it. Build it. Ship it for others.
+70,174 stars
from 6,073 · score 11.16
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
40 repositories by Attention Score · May 7, 2026 – Nov 2, 2026 (UTC)
2.unslothai / unsloth
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.
+16,018 stars
from 62,908 · score 9.68
3.sgl-project / sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
+11,714 stars
from 26,634 · score 9.37
4.owainlewis / awesome-artificial-intelligence
A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.
+3,186 stars
from 13,571 · score 8.07
5.ray-project / ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
+2,008 stars
from 42,166 · score 7.61
6.microsoft / agent-lightning
The absolute trainer to light up AI agents.
+1,963 stars
from 16,902 · score 7.58
7.labmlai / annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
+1,654 stars
from 65,981 · score 7.41
8.OpenPipe / ART
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!
+1,509 stars
from 9,327 · score 7.32
9.d2l-ai / d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
+1,407 stars
from 28,575 · score 7.25
10.Farama-Foundation / Gymnasium
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
+1,003 stars
from 11,760 · score 6.91
11.vwxyzjn / cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
+1,003 stars
from 9,623 · score 6.91
12.DLR-RM / stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
+840 stars
from 13,116 · score 6.73
13.Farama-Foundation / Shimmy
PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama
+725 stars
from 207 · score 6.59
14.wandb / wandb
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
+334 stars
from 10,977 · score 5.81
15.tensorflow / tensor2tensorArchived
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
+305 stars
from 17,167 · score 5.72
16.ShangtongZhang / reinforcement-learning-an-introduction
Python Implementation of Reinforcement Learning: An Introduction
+223 stars
from 14,571 · score 5.41
17.learnsyslab / gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
+214 stars
from 1,980 · score 5.37
18.Farama-Foundation / PettingZoo
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
+170 stars
from 3,379 · score 5.14
19.google-deepmind / acme
A library of reinforcement learning components and agents
+123 stars
from 3,960 · score 4.82
20.Farama-Foundation / HighwayEnv
A collection of environments for autonomous driving and tactical decision-making tasks
+118 stars
from 3,223 · score 4.78
21.ddbourgin / numpy-ml
Machine learning, in numpy
+84 stars
from 16,238 · score 4.44
22.Yvictor / TradingGym
Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.
+70 stars
from 1,857 · score 4.26
23.Toni-SM / skrl
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
+66 stars
from 1,035 · score 4.20
24.learnsyslab / safe-control-gym
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
+62 stars
from 870 · score 4.14
25.opendilab / DI-engine
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
+60 stars
from 3,589 · score 4.11
26.tensorflow / agents
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
+34 stars
from 2,998 · score 3.56
27.google / traxArchived
Trax — Deep Learning with Clear Code and Speed
+29 stars
from 8,270 · score 3.40
28.tensorlayer / TensorLayer
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
+27 stars
from 7,358 · score 3.33
29.vita-epfl / CrowdNav
[ICRA] Crowd-aware Robot Navigation
+27 stars
from 712 · score 3.33
30.catalyst-team / catalyst
Accelerated deep learning R&D
+24 stars
from 3,364 · score 3.22
31.nicrusso7 / rex-gym
OpenAI Gym environments for an open-source quadruped robot (SpotMicro)
+19 stars
from 1,087 · score 3.00
32.benedekrozemberczki / awesome-monte-carlo-tree-search-papers
A curated list of Monte Carlo tree search papers with implementations.
+16 stars
from 701 · score 2.83
33.keras-rl / keras-rl
Deep Reinforcement Learning for Keras.
+14 stars
from 5,534 · score 2.71
34.Ceruleanacg / Personae
📈 Personae is a repo of implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading.
+13 stars
from 1,395 · score 2.64
35.flow-project / flow
Computational framework for reinforcement learning in traffic control
+13 stars
from 1,178 · score 2.64
36.MolecularAI / ReinventArchived
No description provided by the repository host.
+7 stars
from 371 · score 2.08
37.enlite-ai / maze
Maze Applied Reinforcement Learning Framework
+7 stars
from 287 · score 2.08
38.Kismuz / btgym
Scalable, event-driven, deep-learning-friendly backtesting library
+6 stars
from 1,030 · score 1.95
39.deepdrive / deepdrive
Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
+4 stars
from 922 · score 1.61
40.iffiX / machin
Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
+3 stars
from 417 · score 1.39