Rang 1
Tencent-Hunyuan/Prism
NouveauWe propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
+363 étoiles cette semaine
machine-learning
Dépôts Machine learning en tendance
IA & ML
Entraînement, frameworks de deep learning et outils de ML classique.
- Dépôts classés cette semaine
- 119
- Activité par rapport à la semaine dernière
- +5 %
Dépôts classés en Machine learning
+1 autres de Tencent-Hunyuan
Rang 53
AuK: An Open-Source Foundational Model for Speech Generation and Editing
+41 étoiles cette semaine
Rang 2
Learn AI Engineering! Learn it. Build it. Ship it for others.
+4 k étoiles cette semaine
Rang 3
rzc156/dreamforge
NouveauTurn world-model imagination into corrective training data for robot policies — a single-GPU, falsifiable pipeline (SmolVLA · LIBERO · CEM · paired simulator replays).
+130 étoiles cette semaine
Rang 4
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
+430 étoiles cette semaine
Rang 5
speridlabs/iris-3b
NouveauIris-3B: pixel-space generation & general vision learner. A 3B diffusion transformer that generates every pixel directly (no VAE); the same prior, fine-tuned, does monocular depth estimation and 4x image restoration. Paper, weights, training code and demo.
+96 étoiles cette semaine
Rang 6
Interactive, source-linked ML workflow diagrams written by your coding assistant (Copilot, Codex or Claude Code) and opened in VS Code.
+105 étoiles cette semaine
Rang 7
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
+746 étoiles cette semaine
Rang 8
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
+856 étoiles cette semaine
Rang 10
NandhaKishorM/laya
NouveauNon-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
+1,2 k étoiles cette semaine
Rang 11
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
+1,4 k étoiles cette semaine
Rang 12
四十五门真实网课的模块合辑全书 + 思维导图复习笔记 + 逐字稿，全部由 Video2Book 从课程音频重构：518 册教材、603 篇笔记、2,286 份逐字稿，从逐讲精读到考前速查，笔记支持 Markmap / XMind 脑图导入。
+57 étoiles cette semaine
Rang 13
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
+985 étoiles cette semaine
Rang 14
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
+65 étoiles cette semaine
Rang 15
收录最全、更新最快的技能Skills商店：精选原创技能包（涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流），全部打包好可直接安装使用！同时自动抓取GitHub上万个Skills项目，按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains.
+431 étoiles cette semaine
Rang 16
strands-labs/strands-decider
NouveauA small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.
+101 étoiles cette semaine
Rang 17
本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，暂时无法提交到仓库）
+85 étoiles cette semaine
Rang 18
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.
+93 étoiles cette semaine
Rang 19
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
+338 étoiles cette semaine
Rang 20
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
+37 étoiles cette semaine
Rang 21
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
+1,3 k étoiles cette semaine
Rang 22
3,516 curated Figure 1 / teasers from ICLR, ICML, NeurIPS, CVPR, ACL, AAAI (2023-2026), with tier badges and FigureForge retrieval-augmented figure drafting
+95 étoiles cette semaine
Rang 23
ceyyy427/finathink
NouveauFinathink — Financial Research Optimizer for auditable, point-in-time research, mathematical learning, and constrained portfolio analysis.
+39 étoiles cette semaine
Rang 24
向顶会优秀论文学科研｜Oral Paper Skill — 从 883 篇 Oral 论文摘要中“蒸馏”共通做法，用于论文对照改进与学习复盘 · Skill + prompt pack (CN/EN). Learn from 883 Oral paper abstracts to improve your research and writing.
+58 étoiles cette semaine
Rang 25
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
+397 étoiles cette semaine
Rang 26
Curated map of 3,000+ open-source AI agent tools: coding agents, agent frameworks, MCP servers, RAG, memory and local LLMs, sorted by layer and ranked by GitHub stars.
+30 étoiles cette semaine
Rang 28
Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks
+137 étoiles cette semaine
Rang 29
Tensors and Dynamic neural networks in Python with strong GPU acceleration
+885 étoiles cette semaine
Rang 30
Production-grade Rust-native trading engine with deterministic event-driven architecture
+461 étoiles cette semaine
Rang 31
Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭代的知识体系。
+38 étoiles cette semaine
Rang 32
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
+902 étoiles cette semaine
Rang 33
FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, SO-101), simulators and games.
+27 étoiles cette semaine
Rang 34
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
+126 étoiles cette semaine
Rang 35
fstandhartinger/jevbench
NouveauJevBench by Benchmark Heaven: benchmark and leaderboard for AI decision models, measuring typed decision accuracy, calibration, latency and cost.
+29 étoiles cette semaine
Rang 36
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
+503 étoiles cette semaine
Rang 37
A high-throughput and memory-efficient inference and serving engine for LLMs
+512 étoiles cette semaine
Rang 38
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
+666 étoiles cette semaine
Rang 39
SGLang is a high-performance serving framework for large language models and multimodal models.
+306 étoiles cette semaine
Rang 40
FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.
+283 étoiles cette semaine
Rang 41
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
+134 étoiles cette semaine
Rang 42
wfzyx/von
NouveauThe open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
+41 étoiles cette semaine
Rang 43
Remove visible and invisible AI watermarks and provenance metadata from images and video. Python library and CLI for SynthID, C2PA, EXIF, IPTC, XMP, and common generative-AI marks.
+105 étoiles cette semaine
Rang 44
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
+442 étoiles cette semaine
Rang 45
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
+126 étoiles cette semaine
Rang 46
Infrastructure for continually self‑improving agents
+115 étoiles cette semaine
Rang 47
Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt
+69 étoiles cette semaine
Rang 48
NVR with realtime local object detection for IP cameras
+236 étoiles cette semaine
Rang 49
mizorewww/laya-mlx
NouveauNative MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
+99 étoiles cette semaine
Rang 50
Chronos: Pretrained Models for Time Series Forecasting
+89 étoiles cette semaine
Rang 51
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
+120 étoiles cette semaine
Rang 52
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
+314 étoiles cette semaine
Rang 54
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
+45 étoiles cette semaine
Rang 55
Open data and scalable training for long-horizon video world models.
+28 étoiles cette semaine
Rang 56
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
+246 étoiles cette semaine
Rang 57
An Open Source Machine Learning Framework for Everyone
+428 étoiles cette semaine
Rang 58
X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, and multimodal data, combining versatile built-in tools with state-of-the-art AI models and flexible multi-format export.
+90 étoiles cette semaine
Rang 60
The backtesting engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
+82 étoiles cette semaine