Trending repositories: local-ai

16 of 16 repositories

• ggml-org/llama.cpp

  LLM inference in C/C++

  AI summary: A highly optimized, plain C/C++ engine enabling rapid, local inference of large language models across diverse consumer hardware.

  130,295ai-mlC++MITggmlllm-inferencec-cpplocal-ai

• unslothai/unsloth

  Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

  AI summary: A local UI and framework for efficiently training and running large language models.

  77,160ai-mlPythonApache-2.0agentaichatgptdeepseek

• jamiepine/voicebox

  The open-source AI voice studio. Clone, dictate, create.

  AI summary: A local, open-source AI voice generation platform built for real-time speech and global dictation.

  56,144ai-mlTypeScriptMITaicudamlxqwen3-tts

• debpalash/VoiceStudio

  VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

  AI summary: A local-first application for voice cloning, dubbing, dictation, and long-form audio generation across 646 languages.

  53,052ai-mlPythonAGPL-3.0aiaudiobookcudadubbing

• Crosstalk-Solutions/project-nomad

  Project NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all running on hardware you own with no internet required.

  AI summary: A self-contained, offline-first knowledge and education server packed with tools and local AI.

  38,963infrastructureTypeScriptApache-2.0offline-firstself-hostedlocal-aiknowledge-base

• Zackriya-Solutions/meetily

  Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows. Understand How to write meeting minutes

  AI summary: A privacy-first, 100% local AI meeting assistant featuring live transcription, speaker diarization, and summarization.

  31,424productivityRustMITaiai-meeting-assistantllmlocal-ai

• eigent-ai/eigent

  Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

  AI summary: An open-source, local-first Cowork desktop application for building and managing multi-agent AI workflows.

  15,457developer-toolsTypeScriptApache-2.0agent-frameworkagent-skillsagentic-aiagentic-workflow

• Vaibhavs10/insanely-fast-whisper

  AI summary: An opinionated CLI for blazingly fast on-device audio transcription using Whisper Large v3.

  13,058ai-mlJupyter NotebookApache-2.0whisperspeech-to-texttransformersflash-attention

• nearai/ironclaw

  IronClaw is an Agent OS focused on privacy, security and extensibility

  AI summary: A secure, privacy-focused Agent Operating System designed as an extensible personal AI assistant.

  12,634securityRustApache-2.0codeactopenclawrlmrust

• MakazhanAlpamys/Soup

  Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

  AI summary: A lightning-fast, C++ based LLM fine-tuning CLI that utilizes layer streaming.

  8,070ai-mlPythonApache-2.0cliconsumer-gpudpofine-tuning

• leejet/stable-diffusion.cpp

  Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

  AI summary: A pure C/C++ implementation for running Stable Diffusion and other diffusion models locally without Python dependencies.

  7,498ai-mlC++MITaicplusplusdiffusionflux

• Osmantic/ODS

  ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

  AI summary: An automated deployment system that wires together Ollama, Open WebUI, and workflow tools to create a private AI server.

  6,969ai-mlPythonApache-2.0ai-agentsamdcomfyuidocker

• 0xSojalSec/airllm

  Runs 405B LLMs on 8GB VRAM

  AI summary: Run massive language models like 405B Llama 3.1 on consumer GPUs using layer-by-layer streaming without quantization.

  3,060ai-mlJupyter NotebookApache-2.0llminferencevram-optimizationlocal-ai

• zachlatta/freeflow

  Free & fast alternative to Wispr Flow

  AI summary: A free and open-source macOS dictation application providing fast, local AI transcription.

  2,788productivitySwiftMITmacosdictationvoice-to-textlocal-ai

• youssofal/MTPLX

  The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

  AI summary: A native Mac app and CLI tool for running local language models significantly faster utilizing multi-token prediction.

  2,507ai-mlPythonApache-2.0anthropic-compatibleapple-siliconclaude-codeflash-next

• re4/LibreCode

  LibreCode - A Ollama cursor like coding / Reversing Interface

  AI summary: A local, AI-powered IDE featuring integrated decompilation and reverse engineering tools.

  89securityC#Otheraiai-agentscodingcsharp