Havuz

Follow RSI: human-reviewed progress in recursive self-improvement, with a Harness evolution evidence base.

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

Windows utility focused on model download manager, resumable downloads, and local model queue for local AI workflows.

Published: 2026-10-18

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

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

Self-hosted artifact repository manager written in Rust. Hosts, proxies and groups 30+ formats: Docker/OCI, Maven, npm, PyPI, Cargo, Go, Hel

asmsense: a small model that names and describes functions in stripped x86-64 binaries. Open dataset, baselines, and LoRA experiments.

A decision model that returns calibrated answers to yes/no, choice, score and multi-label questions.

🚀🚀 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

Asking for What Was Never Requested: horizontal and vertical proactivity in LLM agents. Need-graph metrics (no LLM judge) and Q&D, which tra

Blazing fast, self-hosted structured decisions for open models with a TypeSafe AI compatible API, written in Rust.

Best AI Workload Orchestrator for Kubernetes Python 2026

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

Local LLMs that run lean, load instantly and keep getting smarter. A from-scratch runtime + model format in Zig: zero-copy mmap, CPU/CUDA/Vu

Raw benchmark logs for Swift-Qwen3.8-27B vs the Qwen3.8-27B BF16 base: every response, score, and config across 9 benchmarks

Local web UI for h3.c — native Metal video/audio generation with MiniMax-H3 on Apple Silicon, no PyTorch or MLX required.

Training-data memorization auditor for fine-tuned LLMs — Trainer/TRL plugin, canary MIA + regurgitation audit, Apache-2.0

Spark-X2.5, yerel çalıştırma ve agent iş akışları için tasarlanmış 1.7B ve 4B boyutlarında açık dil modelleri serisidir.

Neden yükseliyor · Yeni model serisi; uzun context, küçük model boyutu ve agent/coding yeteneklerini aynı anda öne çıkarıyor. README'de 34 günlük yaş, 386 yıldız ve son 28 günde 9 commit ile 2 farklı yazar bilgisi var; bunlar erken ilgi ve güncel çalışma gösteriyor, ancak model performansını bağımsız olarak kanıtlamıyor.

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

ComfyUI top-bar button that reads a workflow's Markdown notes, downloads the models it needs into the right folder, and relinks loader nodes

Dataset abierto de modelos de HuggingFace: metadatos curados y normalizados, licencias clasificadas, parámetros reales, tumbas de modelos re

Offline LLM app for iPhone: run open models from Hugging Face on-device with llama.cpp, MLX, Core ML and Apple Foundation Models. No account

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

Benchmark llama.cpp on your own GPU/CPU boxes and compare against everyone else's — sweep runner, an sha256-keyed index of ~4M GGUF files, a

Rust bindings for Qualcomm GenieX SDK - Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of

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

Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.

A mental-model-first field guide to Audio AI — from raw waveforms to production voice systems. Covers ASR, TTS, audio classification, Transf

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

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

Custom converter: open-weight Hugging Face LLMs/VLMs -> on-device LiteRT-LM (.litertlm), with one-command reproduction

Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, ben

Open-source control panel for the real llama.cpp: see where a model lands in your VRAM before loading, every llama-server flag per model, on

Arabic-first expressive zero-shot speech synthesis — Audar-TTS-V1 (Flash + Turbo + Pro). Voice cloning, expression tags, benchmarks, technic

Learn Agentic AI, Deep Learning, Agentic Engineering, RAG and Multi-Agent Workflows.

Run and serve local models headlessly

Publication-quality LLM architecture figures from config.json — Raschka-style towers, diffs, posters, VRAM math. No weights needed.

The most capable Calibre MCP server — full read/write tools plus multilingual semantic search over your whole ebook library or a single book

A zero-dependency Python module for inspecting and converting coding-agent session files (.jsonl) — Claude Code, Codex, and Pi — into the me

Lynn GitHub 镜像仓 · Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· 主仓 https://github.com/MerkyorLynn/Lynn · 下载 https:

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Self-hosted realtime voice gateway for Hermes Agent. Keep talking while Hermes runs background tasks through local, Gemini Live, and OpenAI

10 legit ways to access major AI models (GPT, Claude, Llama, DeepSeek & more) for FREE — step-by-step guides, no subscription, no card.

Verified multi-source distribution for local LLM weights

Local LLM chat app for Apple Silicon Macs.

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

Your AI/ML research, on one deck — aggregate arXiv/HF/Semantic Scholar papers, star them, and read in-app with cross-device scroll resume.

Local-first AI chat client combining SillyTavern-style character cards, LM Studio-style GGUF model management, Ollama/OpenAI-compatible APIs