ollama
★ 186,871ollama
Run leading open models locally with a simple developer experience.
HYSEN LABS DIRECTORY
#Local AI
Deployment tag · curated repositories and deep analysis.
Rising this week
Largest Star gains over the past seven days, from our daily GitHub snapshots.
ggml-org/llama.cpp+1,292 this week
ollama/ollama+855 this week
open-webui/open-webui+631 this week
RVC-Boss/GPT-SoVITS+574 this week
Mintplex-Labs/anything-llm+236 this week
Latest discussions
Posts on Hacker News, dev.to and Lobsters that link to a project listed here.
- Why Your 19.5GB LLM Crawls on 24GB VRAM (The KV Cache Fix)dev.to · Nov 14 · 3 points · llama.cpp
- Benchmarking the Gemini Decisions APIdev.to · Nov 13 · 11 points · llama.cpp
- Jensen is out. CUDA isn't. A Developer's Guide to Everything Nvidia Builtdev.to · Nov 13 · 7 points · llama.cpp
- Six Serving Engines on Four Accelerators: Gemma 4 E2B on an RTX 3050, a T4, an L4 and a TPU v5edev.to · Nov 13 · 14 points · llama.cpp
- llama.cpp v1.0Hacker News · Nov 13 · 5 points · llama.cpp
6 curated open-source projects
open-webui
★ 158,573open-webui
Open WebUI is a self-hosted AI interface that runs entirely offline, supporting Ollama and OpenAI-compatible APIs with a built-in inference engine for RAG.
ggml-org
★ 134,864llama.cpp
llama.cpp runs LLM inference in plain C/C++, serving models locally through a REST API and web UI with multimodal support in its llama-server.
Mintplex-Labs
★ 68,248anything-llm
Local-first, all-in-one AI desktop app for chatting with your documents and running AI agents, with multi-user support and no setup friction.
RVC-Boss
★ 64,973GPT-SoVITS
GPT-SoVITS is a few-shot voice cloning and TTS WebUI that fine-tunes a speaker's voice from one minute of audio and supports zero-shot synthesis from a five-second sample.
ggml-org
★ 55,166whisper.cpp
whisper.cpp is a dependency-free C/C++ port of OpenAI's Whisper speech-recognition model, optimized for Apple Silicon and supporting CPU-only inference on many platforms.