Havuz

A curated collection of AI learning materials

Crypto liquidity detection & algorithmic trading bot. Order book analysis, stop-loss clusters, liquidity sweeps. Multi-exchange (Binance, By

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

PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ wi

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

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.

Learn what AI skills are and how to design, structure, and use them in real-world agent systems.

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

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.

Open-source personalized scientific discovery feed powered by arXiv, OpenAlex, PubMed and more.

Voynich Manuscript Decoded: Elu-Sinhala Phonetic Transcription & Vocabulary Toolkit 2026

Top 6 AI Paradigms Fighting for Survival in 2026

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

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

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

Turn Android Termux into an autonomous AI agent and security orchestrator. Powered by a local ReAct framework with 50 system tools and MCP s

PeakPulse AI — Real-Time Financial Market Anomaly Detection & Time-Series Machine Learning Engine

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

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

Turn any AI agent into a research co-scientist: 280+ open-source agent skills for literature reviews, hypotheses, experimental design, data

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

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional

AI/ML Engineer in progress — LLM, RAG, Computer Vision. Open to full-time AI Engineer roles.

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

Mechanical Governance for LLM Decisions — model-agnostic governance regimes (R1/R2/R3), hard gates, entropy commit-reveal and governance met

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

开源研究管道 —— 文献综述、新颖性生成、引用验证与对抗性审查 | Open-source research pipeline — literature review, novelty generation, citation verification, and adversar

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker

Comprehensive illustrated notes for Stanford CS336 (Spring 2025) — Language Modeling from Scratch. Live: qihongruan.github.io/cs336/

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

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.

Best Chrome Extension for JSON API Debugging and Web Security Testing 2026

High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.

Automated Bee Swarm Simulator 2026 Memory Script with ESP and Movement Tools

Strands-based agents and harnesses for agentic benchmarks.

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

📚🔭 Your personal research radar — an LLM-powered tool that auto-aggregates the latest papers for your keywords across arXiv / Crossref / Sem

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

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

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。

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

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

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

Hybrid recommender system + RAG chatbot for IT courses (FastAPI + Express/TS + PostgreSQL), with an independent Data Lakehouse module (Spark

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