# ZHangZHengEric/Sage

Multi-Agent System Framework For Complex Tasks

Repository: https://github.com/ZHangZHengEric/Sage
Canonical: https://ross.abutalabs.com/products/zhangzhengeric-sage
Homepage: https://zhangzhengeric.github.io/Sage/
Language: Python
License: MIT
License Family: permissive
Topics: agents, llm, manus, muilt-agents, ai, workflow
Last push: 2026-09-03T02:01:38+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 86, longevity 33
- inputs: {"age_days": 465, "days_push": 0, "days_rel": 99, "gap_med": 1.0, "n_releases_24m": 41}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1213, forks 101 (observed 2026-09-03T02:15:08.668210+00:00)

## What it is
Sage is a Python-based multi-agent framework and platform for planning, executing, and delivering complex tasks with LLM-powered agents. It provides a visual workbench, browser automation, MCP tool integration, sandboxed execution, and omnichannel messaging delivery across desktop, web, CLI, and Chrome extension surfaces.

## Use cases
- orchestrate multiple llm agents to complete complex tasks
- automate browser workflows with ai agents
- run scheduled recurring agent jobs
- deliver agent results to wechat, feishu, or dingtalk
- build a self-hosted manus-like agent platform
- execute agent code in a sandboxed environment
- inspect agent tool outputs and files in a visual workbench

## When to choose
- you need a production-ready multi-agent platform with planning, execution, and self-check loops
- you want integrated browser automation, MCP tools, and IM delivery in one stack
- you need sandboxed agent execution with enterprise auth and deployment options

## When to avoid
- you only need a lightweight single-agent library with minimal dependencies
- you want a framework with a large established ecosystem and long-term track record
- you need non-Python-first agent orchestration

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, chatbot, mcp, web-scraping, scheduling, chat-interface
- domain: large-language-models, developer-tools
- platform: python, cross-platform, cli, browser-extension, self-hosted
- tags: multi-agent, llm-agents, browser-automation, im-integration, sandboxed-execution, task-automation, manus-style, visual-workbench, ai-agents, automation, desktop, web-server, docker

## Member repositories
- ZHangZHengEric/Sage (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:08.668210+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:18:57.461414+00:00, confidence not recorded.
  - readme: https://github.com/ZHangZHengEric/Sage (fetched 2026-09-03T02:15:08.668210+00:00, sha 77a6e152f200)
  - homepage: https://zhangzhengeric.github.io/Sage/ (fetched 2026-08-29T12:26:44.656601+00:00, sha f20697464692)
- Data as of 2026-08-30T08:39:29.467469+00:00.