| Name | Version | Summary | date |
| pygpt-net |
2.6.40 |
Desktop AI Assistant powered by: OpenAI GPT-5, GPT-4, o1, o3, Gemini, Claude, Grok, DeepSeek, and other models supported by Llama Index, and Ollama. Chatbot, agents, completion, image generation, vision analysis, speech-to-text, plugins, internet access, file handling, command execution and more. |
2025-09-06 02:44:01 |
| autoclean-icvision |
0.1.3 |
Automated ICA component classification using OpenAI Vision API for EEG data |
2025-09-05 08:02:42 |
| achatbot |
0.0.24.post5 |
An open source chat bot for voice (and multimodal) assistants |
2025-09-04 16:40:06 |
| parllama |
0.4.0 |
Terminal UI for Ollama and other LLM providers |
2025-09-03 01:33:37 |
| volute-ppt |
1.4.6 |
Advanced MCP server for PowerPoint automation - comprehensive editing, analysis, and multimodal AI integration with intelligent text processing and native bullet conversion |
2025-08-31 19:15:03 |
| nexusai-sdk |
1.0.1 |
Python SDK for NexusAI - AI Agent Platform for Businesses |
2025-08-31 13:54:10 |
| halo-video |
1.0.8 |
Interactive Video QA System - AI-powered YouTube video analysis with question-answering capabilities using Google Gemini Vision API and audio transcription. |
2025-08-31 00:30:32 |
| volute-xls |
1.4.0 |
MCP server for Excel analysis and multimodal AI integration - comprehensive metadata extraction and sheet image capture for agents |
2025-08-30 06:43:14 |
| az-ai-healthcheck |
0.1.5 |
Lightweight health checks for Azure OpenAI and Azure AI Vision |
2025-08-28 02:19:26 |
| azure-ai-healthcheck |
0.1.1a2 |
Lightweight health checks for Azure OpenAI and Azure AI Vision |
2025-08-27 04:13:04 |
| volutemcp |
1.1.1 |
MCP server for PowerPoint analysis and multimodal AI integration - comprehensive metadata extraction and slide image capture for agents |
2025-08-27 01:19:14 |
| pdf2markdown |
0.2.0 |
Python library and CLI tool that leverages LLMs to convert technical PDF documents to well-structured Markdown |
2025-08-17 20:03:08 |
| hume |
0.11.3 |
A Python SDK for Hume AI |
2025-08-14 17:32:59 |
| llm-markdownify |
0.3.0 |
Convert PDFs, images to high-quality Markdown using Vision LLMs. |
2025-08-13 22:07:30 |
| cmn-ai |
0.1.0 |
A comprehensive machine learning library with utilities for vision, text, and tabular data |
2025-08-12 15:35:55 |
| zmkj-rknn-yolov8 |
8.0.151.post2 |
自用rknn yolov8 版本 只修复了 weights_only=False 问题 来源https://github.com/airockchip/ultralytics_yolov8 8.0.151 v1.6分支 |
2025-08-11 11:12:58 |
| screenmonitormcp-v2 |
2.0.9 |
A revolutionary Model Context Protocol (MCP) server that gives AI real-time vision capabilities and enhanced UI intelligence power |
2025-08-06 14:42:51 |
| pyrebel |
1.1.14 |
A pure python library that implements abstraction of data. |
2025-07-26 10:16:35 |
| rfdetr |
1.2.1 |
RF-DETR |
2025-07-24 11:54:04 |
| boxmot |
15.0.2 |
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models |
2025-07-23 20:43:35 |