Havuz

VoiceStudio, yerel speech modellerini masaüstü uygulamasında voice cloning, text-to-speech, transcription ve video dubbing gibi iş akışlarıyla bir araya getiriyor.

Neden yükseliyor · 171 günde 37.761 yıldıza ulaşması dikkat çekici kullanıcı ilgisine işaret ediyor; kapsamlı yerel voice iş akışları ve ElevenLabs alternatifi olarak konumlanması bu ilgiyi açıklayabilir. Son 28 gündeki 1.505 commit yüksek aktivite gösterse de yalnızca 6 farklı yazar görünmesi, bu hareketin geniş katkıcı tabanına yayıldığını kanıtlamıyor.

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

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

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw

FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs

A benchmark for AI-driven CAD generation and editing

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

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

Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Fac

Open-source CLI, API, web UI, and reproducible benchmarks for probabilistic AI-generated image detection.

From PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native, cross-platform, and built for the best possible us

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

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

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

Building an Image-to-Video (I2V) Model from Scratch

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

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

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA,

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

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

Verified multi-source distribution for local LLM weights

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

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

55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audit, feature development, frontend design, MCP

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

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

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

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

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI

Build your own offline AI from any documents. Free. No coding. LoRA fine-tuning + RAG + GGUF export.

Hugging Face recipes: run OCR, transcription, classification, embeddings and more over a Hub dataset in one command, locally or on HF Jobs.

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

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

Local LLM inference on Xbox Series S in Developer Mode: llama.cpp (GGUF) + ONNX Runtime GenAI, an OpenAI-compatible LAN endpoint (off by def

Cache Commander — a TUI and MCP server to explore, audit, and clean developer cache directories. Scan for CVEs, find outdated packages, recl

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

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

The AI study agent that learns how you learn — RL picks the action, FSRS picks the timing, the LLM only writes the quizzes. Chrome extension

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

Run and serve local models headlessly

One free AI endpoint, every free tier behind it. Local OpenAI-compatible gateway routing across OpenRouter, Groq, NVIDIA NIM, Cloudflare Wor

Best AI Workload Orchestrator for Kubernetes Python 2026

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

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

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

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

Generate degraded speech datasets for noise-robust ASR benchmarking

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

A tiny language model that talks like a house cat named Miso.

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID