icowan
Follow
Starred repositories
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
A TTS model capable of generating ultra-realistic dialogue in one pass.
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent & VSCode Agent (And other Open Sourced) System Prompts, Tools & AI Models.
Lightweight coding agent that runs in your terminal
An open protocol enabling communication and interoperability between opaque agentic applications.
LAYRA is a ready-to-use visual RAG system with a complete web UI built with Next.js and FastAPI, preserving document layout, tables, paragraphs, and graphical elements without any structural fragme…
Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.
Force1ess / python-pptx
Forked from scanny/python-pptxCreate Open XML PowerPoint documents in Python
Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
Python based web automation tool. Powerful and elegant.
Synthesizing High-quality Text-to-SQL Data at Scale. SynSQL-2.5M is the first million-scale cross-domain text-to-SQL dataset.
A Conversational Speech Generation Model
A lightweight, powerful framework for multi-agent workflows
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
🤖 Open-source GenBI AI Agent that empowers data-driven teams to chat with their data to generate Text-to-SQL, charts, spreadsheets, reports, dashboards and BI. 📈📊📋🧑💻
No fortress, purely open ground. OpenManus is Coming.
Developer-friendly, embedded retrieval engine for multimodal AI. Search More; Manage Less.
Agno is a lightweight library for building Agents with memory, knowledge, tools and reasoning.
Wan: Open and Advanced Large-Scale Video Generative Models
FlashMLA: Efficient MLA decoding kernels