Havuz

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

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

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

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

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

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

Local-first reading workspace for technical papers — select an equation, figure, or passage and get grounded, step-by-step walkthroughs (wit

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

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from

On-device subject cutouts, image labels, and OCR for React Native. Apple Vision (iOS) · Google ML Kit (Android). Built with Nitro Modules.

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

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

Strands-based agents and harnesses for agentic benchmarks.

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

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

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

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

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

AI-powered real-time object detection, tracking, and video intelligence platform using YOLO and computer vision.

PromptLedger, prompt şablonlarını fingerprint ile sürümleyip aday yanıtları karşılaştıran ve sonuçları tekrarlanabilir raporlara dönüştüren bir Python aracı ile Go CLI sunuyor.

Neden yükseliyor · 25 günlük bir repo için 35 yıldız dikkat çekiyor; ancak son 28 günde yalnızca 1 commit ve 1 farklı yazar var. Bu nedenle ilginin kalıcı benimsemeye dönüştüğünü gösteren yeterli aktivite kanıtı henüz yok.

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

A free textbook on building an LLM inference stack from scratch in Rust.

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

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

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

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

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab.

First general Wiki MCP following google's Open Knowledge Format. Let your agent to use, manage, maintain, and health check the wiki (knowled

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

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

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

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.

A dependency-free Python genetic-algorithm engine with pluggable fitness criteria — the reusable search core for an LLM/AI autoresearcher.

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

The Kimi K3 and DeepSeek-V4-Flash-0731 architectures, reimplemented from scratch in pure Rust (zero dependencies) and verified 1:1 against t

Run AI models on Apple Silicon and Raspberry Pi

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

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

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

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

Combine the results from a panel of models into an enhanced response

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

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

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

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

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

A narrative walk through 90 years of AI history, paper by paper. 66 chapters from Turing 1936 to Blackwell 2025.