#python #ai #ai_agent #ai_infra #kubernetes #sandbox

OpenSandbox is a general-purpose sandbox platform that lets you safely run AI applications, code, and agents in isolated environments. It provides multi-language SDKs for Python, Java, and JavaScript, making it easy to integrate into your projects. The platform supports Docker and Kubernetes runtimes, so you can run sandboxes locally or at scale. Key benefits include running code generated by AI models safely, executing data analysis, automating browser tasks, and training AI systems without risking your main system. Whether you're building coding agents, testing applications, or letting AI handle complex tasks, OpenSandbox gives you a secure, controlled space to experiment and execute code without side effects.

https://github.com/alibaba/OpenSandbox

#python #agent #android #app #automation #copilot #gui #mllm #mobile #mobile_agents #multimodal #multimodal_agent #multimodal_large_language_models

Mobile-Agent-v3.5 is Alibaba's top GUI agent family using GUI-Owl 1.5 models (2B to 235B sizes) for automating desktop, mobile, and browser tasks like stock checks, bookings, or document creation with planning, reflection, and memory. Try free online demos on ModelScope or Bailian, or use limited-time APIs—no setup needed. It leads 20+ benchmarks for real-world use. You benefit by saving time on repetitive tasks, boosting productivity, and handling complex operations hands-free across devices.

https://github.com/X-PLUG/MobileAgent

#python

Hermes Agent is a free, open-source AI that installs on your server, learns your projects and preferences over time, and handles tasks via Telegram, Discord, Slack, WhatsApp, or terminal. It builds reusable skills from solved problems, runs scheduled automations like daily reports, and uses secure sandboxes (Docker/SSH) for safe code execution with any AI model. You benefit by getting a smart, growing assistant that automates work, remembers everything, and stays reachable anywhere—saving hours on repetitive tasks while boosting productivity.

https://github.com/NousResearch/hermes-agent

#python #mcp #mcp_server #open_data #opendata

Data.gouv.fr MCP Server lets AI chatbots like Claude or ChatGPT search, explore, and analyze over 74,000 French open datasets via simple questions, such as "Show latest Paris population data" or "Find real estate prices," without manual browsing. Connect easily to the free public endpoint https://mcp.data.gouv.fr/mcp—no API key needed. You benefit by getting instant, accurate access to public data like company info, metrics, and resources, saving time on research or apps and enabling quick insights from France's top-ranked open data platform.

https://github.com/datagouv/datagouv-mcp

#python #agent_skills #ai_scientist #bioinformatics #chemoinformatics #claude #claude_skills #claudecode #clinical_research #computational_biology #data_analysis #drug_discovery #genomics #materials_science #metabolomics #proteomics #scientific_computing #scientific_visualization

Claude Scientific Skills offers 148+ ready-to-use tools for AI agents like Cursor or Claude Code, covering biology, chemistry, drug discovery, clinical research, ML, and 250+ databases (PubMed, ChEMBL, etc.). Easy setup: clone the GitHub repo and copy folders to your skills directory for automatic use in complex workflows like single-cell analysis or virtual screening. You save days on setup, get reliable code, and run multi-step science faster on your desktop.

https://github.com/K-Dense-AI/claude-scientific-skills

#python #agent #chatbot #large_language_models #llm #llm_agent #mcp #multi_agent #multi_modal #react_agent

AgentScope is a simple, production-ready framework to build AI agents fast. Install with `pip install agentscope` (Python 3.10+), then create ReAct agents with tools, memory, voice, human steering, multi-agent workflows, and finetuning in 5 minutes. It supports realtime voice, A2A protocols, RL training, and easy deployment locally, in cloud, or Kubernetes. You benefit by quickly making robust, scalable agents for tasks like games, research, or chats without complex coding, saving time and enabling real-world apps.

https://github.com/agentscope-ai/agentscope

#python #agent #ai_agents #memory #memoryscope #rag #reme

ReMe is a memory toolkit for AI agents with file-based (Markdown files for easy editing) and vector-based systems to fix limited context and stateless chats. It auto-summarizes talks, saves key facts like preferences, and recalls them next time using hybrid search. Install via `pip install reme-ai`, set API keys, and use ReMeCli or Python code for smart agents. You benefit by building persistent, learning agents that remember your needs, work faster on repeat tasks, and feel more natural without starting over.

https://github.com/agentscope-ai/ReMe