Private local AI assistant for your desktop. Voice and text chat, personal memory, dictation and MCP tools. Runs offline with Ollama or OpenAI-compatible servers on macOS, Windows and Linux.
Repository Index
89,073 visible repositories in the index
3,265–3,288 of 7,521 · Most stars
Empowering RAG with a memory-based data interface for all-purpose applications!
- memory
- rag
- long-llm
A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness
- audio
- automatic-speech-recognition
- multilingual
- speaker-diarization
A library for training and deploying machine learning models on Amazon SageMaker
- aws
- mxnet
- tensorflow
- machine-learning
Open-source low code data preparation library in python. Collect, clean and visualization your data in python with a few lines of code.
- dataprep
- data-science
- datapreparation
- dataconnector
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
- image-editing
- reasoning
- visual-reasoning
Django 5, React, Tailwind 4 with Python 3 and Webpack project boilerplate
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
- agentic-ai
- agentic-workflow
- agents
- function-calling
An open-source desktop app for generating videos with LTX models
- generative-ai
- ltx
- ltx-2
- non-linear-editing
Web Crawling and RAG Capabilities for AI Agents and AI Coding Assistants
Ongoing research training transformer language models at scale, including: BERT & GPT-2
The repository host gives no description.
Prompts, workflows and more for agentic engineering
GlobalBuildingAtlas: an open global and complete dataset of building polygons, heights and LoD1 3D models
Python package for scraping recipes data
- data-extraction
- food
- html-parsing
- json-ld
The implementation of DeBERTa
- bert
- deeplearning
- representation-learning
- roberta
[TPAMI 2026🔥] Helios: Real Real-Time Long Video Generation Model
- acceleration
- diffusion
- diffusion-models
- image-to-video
📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion
Unsupervised single image depth prediction with CNNs
AIWriteX - 微信公众号全自动AI工具：全网热搜舆情聚合+趋势分析+爆款选题+文章采集+一键生成排版发布 | AI自动配图 | 去AI味、过朱雀检测 | 支持小红书/百家号/头条等多平台 | 洗稿润色支持多账号 | 专家赛道 | 小绿书贴图 | 短视频文案 | 手机控制 | 小说连载 | 短剧剧本 | 爆文10w+神器
- crewai
- weixin
- wx
- ai-wx
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
- quantization
- pruning
- dorefa
- twn
official repository of aiXcoder-7B Code Large Language Model
Simplified packaging of Python modules
Translate GPU shaders and compute kernels between GLSL, HLSL, Metal, SPIR-V, Slang, CUDA and HIP, and to WGSL, through the CrossGL IR