Havuz

Open, probabilistic day-ahead load forecasts for the US power grid. Chronos-2 fine-tuned on 7 years of EIA-930 data across all 53 reporting

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

Transformer inference via unconventional compute: a single algebraic primitive, a tag-system scheduler, and Apple's Neural Engine through co

Open-source research intelligence for CS papers — track what matters, who drives it, what to read first, and where the research gaps are.

How hard can it be to implement a diffusion language model by hand? Easier than I thought, actually.

Production-ready RAG assistant for Moodle — containerized with Jenkins CI/CD on AWS.

ParseBench - A Document Parsing Benchmark for AI Agents

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula

A knowledge graph and meta-learning framework for context-aware automated feature engineering

Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU

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

Turn any song into playable piano sheet music. Paste a YouTube link or upload audio — get a PDF score. Open-source pipeline: Basic Pitch tra

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

🩺 Diabetes Detector: An ML diagnostic tool using a Random Forest Classifier to predict diabetes risk. FastAPI backend + Next.js frontend, wi

A Personalized Federated Learning (PFL-HCare) framework for IoT healthcare. Features MAML meta-learning, Differential Privacy (RDP), and gra

🛡️ A modern, AI-powered WAF with visual forensic playback via rrweb. Protect your web apps with LLM-driven threat detection, real-time visua

Self-learning AI agent that gets smarter and cheaper over time. Routes between local and cloud LLMs, learns from every interaction, remember

A curated collection of AI learning materials

A self-improving knowledge base about LLM agent infrastructure

Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently ro

PyTorch-native framework for fault-tolerant distributed training of foundation models on AI clusters

A free, open GenAI curriculum built from scratch. Start from zero, build real projects, and work your way up to production AI systems.

AI model that animates any SVG into Lottie with 3-4x fewer tokens than OmniLottie (CVPR 2026). Upload SVG → get animated .lottie. 3B model,

Ultra-Sparse Adaptation of 1-Bit LLMs via XOR Patches

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

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without ca

Decoding Claude Code's leaked 512K-line source — hidden features, 43 tool definitions, system prompts, architecture patterns

Unified Python/CLI time-series decomposition library with native acceleration, multivariate workflows, and machine-readable outputs.

🌟 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。

Reproducible OpenEnv-compatible reinforcement-learning environments for social-media integrity moderation.

🪞 Make your agents recursively self-improve

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

AI Agent 工程师面试资料库 - 国内大厂面经、岗位要求、高频面试题

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

Make your agents learn from experience. One protocol for weights, harness and routing.

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

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

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

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

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

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

[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

Machine learning powered Karaoke app (with scores!)

Agent-native streaming infrastructure. The streaming runtime built for non-human broadcasters.

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

AI guardian for manual crypto traders — risk monitoring, strategy validation & emotional trading detection. No trade execution.

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

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p

Autonomous prediction-market trading bot: ML ensemble + LLM signals, real-time WebSocket alerts

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur