Havuz

Reactant-first training for Lux models: declare the experiment, compile once, train without boilerplate.

Runs Hugging Face ONNX models on any Nx backend, with no per-architecture code

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

Paxeer X is a Distributed HyperState Machine for payments, code execution and intent routing. Designed for Machines and the Users operating

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Synthetic fraud graph generator for benchmarking graph-based fraud detection models in financial services.

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

🌟 推理王国：关于 AI 推理机制的思想实验手册。从信息论、符号逻辑与表示学习出发，系统剖析大模型“智能”的本质。

🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows,

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming)

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE

Free open source disk cleaner for developers. Clean Hugging Face, Ollama, npm, pip, conda, Docker caches, app leftovers, and junk files on m

An educational macOS app: build and chat with a tiny language model, trained on your Mac

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

AI crypto trading bot with deep neural network (84.9% accuracy, 25 coins). BiLSTM + Attention trained on GPU. Bybit, Binance, OKX, Gate.io.

Personal academic and research portfolio focused on AI, low-resource Urdu NLP, RAG systems, machine learning, and computer science.

Universal local LLM runtime. Drop-in Ollama replacement with HuggingFace integration, pipelines, structured output. Free & open source.

📊 Daily auto-updated snapshots of all Arena AI (LMSYS Chatbot Arena) leaderboards — LLM, Vision, Code, Video, Image & more. Structured JSON

🪁 Read any manga in your language directly in-browser. 100% local-first AI translation with WebGPU OCR, clean background inpainting, and stu

Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests

Cooking AGI / AGI 大锅烩 · Bilingual (English / 中文) ML & LLM notes with worked examples, step-by-step figures and coding practice. Free to read

LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.

数学建模项目与资料库：竞赛论文、可运行代码、历年赛题、优秀论文与常用模型案例

Stanford CS336《从头构建大语言模型》2026 中配版：18 篇中文技术博客 + 19 篇「图-字幕」原始文稿，基于 video2blog-skill 整理。

Ground Truth: A working developer's path into AI and machine learning, with interactive explanations, reproducible Python labs, and practica

One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.

Custom APRL machine-learning algorithm + a curated ML knowledge base of 923 papers, lectures, and explainers. NumPy classifier/regressor, te

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apach

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

Self-Tuning Multi-Agent AI Trading System 2026: 8-Source Signal Fusion & Kronos Model

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression wit

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graph

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. P

Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.

Strands-based agents and harnesses for agentic benchmarks.

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on

📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

Wiki built using Karpathy method containing information about TPU performance optimizations and hooking it up to autoresearch optimization e

Auditing algorithmic bias in criminal justice, hiring, lending, healthcare, welfare, and tenant screening: 7 open-source audits, measurable

AI Image Generator is a powerful and user-friendly desktop application designed to help creators produce stunning, high-quality artwork, pho

Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)

Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence