Stars
A user-friendly, multi-platform GUI for managing and running CrewAI agents and tasks. Supports Conda and virtual environments, no coding needed.
Zulip server and web application. Open-source team chat that helps teams stay productive and focused.
A cool, modern and responsive django admin application based on bootstrap 5 that brings AI to the Django admin - https://baton.sqrt64.it/
Saleor Core: the high performance, composable, headless commerce API.
Robust Speech Recognition via Large-Scale Weak Supervision
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
No fortress, purely open ground. OpenManus is Coming.
An open-sourced end-to-end VLM-based GUI Agent
MCP server that interacts with Obsidian via the Obsidian rest API community plugin
MCP server for fetch web page content using Playwright headless browser.
MCP server for connecting agentic systems to search systems via searXNG
🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Production-ready platform for agentic workflow development.
为了解决国内无法访问插件商店和主题商店的问题，我写了这个代理服务器，可以部署在netlify上运行。
A dynamic user interface for adjusting theme, plugin, and snippet CSS variables within Obsidian
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
Easily add PyGWalker visualizations to your Django applications
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括335个大模型，覆盖chatgpt、gpt-5.2、o4-mini、谷歌gemini-3-pro、Claude-4.5、文心ERNIE-X1.1、ERNIE-5.0-Thinking、qwen3-max、百川、讯飞星火、商汤senseChat等商用模型， 以及kimi-k2、ernie4.5、minimax-M2、deepseek-…
Django-Vue3-Admin is a comprehensive basic development platform based on the RBAC (Role-Based Access Control) model for permission control, with column-level granularity. It follows a frontend-back…
Official electron build of draw.io
一款电脑语音输入工具，运行后，按下大写锁定键超过 0.3 秒，就开始语音识别，松开按键之后，自动输入识别结果。