Havuz

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a plat

A desktop-native Windows system tray Telegram bot that monitors AniList for new anime announcements and releases with network auto-recovery,

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

Windows utility focused on cuda setup, nvidia local AI, and cuda environment for local AI workflows.

Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch).

Offline multi-speaker meeting-speech toolkit: planted-ground-truth synthetic meeting factory, VAD, speaker embeddings, diarization (AHC/spec

Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: System 1.5 decision models that think in loops, no

Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen

Local decision engine with typed, calibrated outputs (Noul/Choice/Score): cheap→strong cascade, ECE/Brier calibration, SystemOne protocol in

Iris-3B pixel-space text-to-image on Apple Silicon GPUs: Metal-optimized engine, native macOS app, CLI, Python and local HTTP API

This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention wh

Autonomous AI trading system powered by Kronos. Forecasts markets, builds portfolios and paper-trades automatically with GitHub Actions.

Tiny, fast Brazilian Portuguese text-to-speech (21M params)

AnyFlow - flow-matching video generation: training, inference and VBench evaluation for t2v and i2v models.

Official implementation of "Unifying Distributional Training for One-Step Visual Generation" (MGFlow).

A fancy NVIDIA GPU monitor for the terminal. One Python file, no dependencies.

Composable LLM decoding on the probability simplex: library and paper code.

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security

Qwen-Image-2.1 ile Apple Silicon üzerinde yerel görsel üretimi ve çoklu görsel düzenleme sağlayan bir CLI ile helmstudio’ya bağlı web arayüzü sunuyor.

Neden yükseliyor · Beş günlük yaşında 55 yıldız ve son 28 günde 12 commit, iki farklı yazar görünüyor. Bu ilk ilgi ve geliştirme hareketliliğine işaret ediyor; ancak kısa geçmiş ve sınırlı yazar sayısı benimsenme ya da kalıcı bakım kanıtı değil.

Scaler 2 Music Theory Tool 2026: Direct DAW Integration for Windows 10 and 11

Best AI Workload Orchestrator for Kubernetes Python 2026

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.

Hardware-aligned latent deliberation framework decoupling System 2 continuous reasoning from System 1 autoregressive decoding.

Static reproducibility checks, experiment replay, and verification for ML pipelines.

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an

🎙️ Adaptive Audio Authentication Engine: Multi-layer voice biometric system with deepfake detection, speaker verification (ECAPA-TDNN), ASR

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.

Halo is an open-source framework built by White Circle for training large language and multimodal models

Pyramis-L3D: hierarchical sparse attention research prototype (code only; weights on Hugging Face)

A self-hosted studio for generating images, video, and audio with diffusion models.

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

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，

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

Local text-to-speech: 28 voices, 10 languages, voice cloning, SDKs for Python, Swift, Go, Rust and TypeScript

Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning

AuK, tek bir doğal dil talimat arayüzüyle konuşma üretimi ve düzenleme görevlerini gerçekleştiren açık ağırlıklı bir speech modelidir.

Neden yükseliyor · Yeni yayımlanmış bir model olarak kısa sürede 1308 yıldız almış; son 28 gündeki 30 commit ve 5 farklı yazar da aktif geliştirmeye işaret ediyor. README ayrıca vLLM-Omni, SGLang-Omni ve audio.cpp desteğini, modelin farklı inference ekosistemlerine taşınmasını sağlayan somut ilgi göstergeleri olarak listeliyor.

AI watermark removal built for Apple Silicon. SynthID-class pixel regeneration, visible vendor labels and provenance metadata, with every pi

An optimized handwritten digit recognition model delivering exceptional accuracy, high-speed performance, and compatibility with low-end har

Interactive, animated architecture maps for any Hugging Face model — no weights downloaded

GlobalPointer-BiLSTM reference implementation for joint entity and relation extraction

Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.

โคลนเสียงพูดภาษาไทยด้วย JaiTTS (F5-TTS) — ติดตั้งคำสั่งเดียว ใช้งานผ่านหน้าเว็บได้ทันที · Thai voice cloning made easy: one-command setup, l

NeuralForge is an end-to-end LLM fine-tuning & serving platform. It leverages LoRA (PyTorch/Hugging Face) for domain adaptation, cutting err

I switched phones and found thousands of WhatsApp photos waiting for me, mostly memes and screenshots. This finds the ones worth keeping: se

Build and train a mini Kimi K3 from scratch — a pure-PyTorch playground from a custom 88M model to 2T-scale LLM profiles.