Sage

Active
GitHub Python MIT

Description

Multi-Agent System Framework For Complex Tasks.

Key Features

  • Planning to Delivery: Built-in planning, execution, self-check, memory recall, and tool suggestion agents for complex task completion
  • Multi-Entry Product Surface: Use Sage from desktop, web, CLI, and Chrome extension depending on the workflow
  • Automation & Recurring Tasks: Run scheduled jobs, questionnaire-driven collection flows, and long-running operational tasks with progress visibility
  • Omnichannel IM Integration: Connect WeChat, WeCom, Feishu, and DingTalk with message and file delivery support
  • Unified Tooling System: Combine built-in tools, Skills, MCP servers, browser automation, search, and image generation in one execution stack
  • Sandboxed Execution: Local, passthrough, and remote sandbox options for safer agent runtime isolation

Use Cases

💡 Enterprise multi-agent collaboration and task decomposition scenarios
💡 Automated task execution result and file delivery via IM channels
💡 Scheduled operations and data collection workflow automation
💡 Interactive development through visual workbench on desktop or web

Tags

agents ai llm manus muilt-agents workflow multi-agent python

Categories

🧠 Multi-Agent 🔄 Workflow

Quick Start

Clone the repo, set LLM API key environment variables, run ./scripts/dev-up.sh to start the Web server, and open localhost:5173. Desktop installers are available from GitHub Releases. For CLI, install with pip install -e . and run sage run.
Visit GitHub Visit Website

Related Projects