Skip to content
Agents tracked: 258 Downloads (7d): 219M up 9.4% GitHub stars: 5.5M VS Code installs: 148M Releases (7d): 282 Agent pull requests (last week): 940K Updated Oct 6, 2026

AgentScope by Alibaba (Tongyi Lab)

Agent frameworks and SDKs #86 overall#20 in categoryOpen source · Apache-2.0
Pulse Score
40 / 100
Rank #86 of 258
Downloads, last 7 days
27.5K
up 18.6% vs previous week
Downloads, last 30 days
206K
— vs previous 30 days
GitHub stars
32.8K
about +40 a day
Latest release
2.0.9
8d ago · 2 in 30 days
Price
Free (OSS)
checked Oct 6, 2026

Overview

A Python framework for building multi-agent applications with ReAct agents, tool and MCP management, model abstractions, pipelines and human-in-the-loop controls.

AgentScope was downloaded 27.5K times from PyPI in the week ending Oct 4, 2026, up 18.6% on the week before. Its download count moved to a different level overnight on Sep 15, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 32.8K stars, 2,053 of them added in the last 30 days. The latest stable release is 2.0.9, published Sep 28, 2026; there were 2 stable releases in the past 30 days.

AgentScope usage and attention over time

Downloads per dayPyPI, 7-day average 3,930/day
GitHub starsrunning total 32.8K
Website rankTranco list; a lower rank means more traffic #494,808

Download the raw daily series: agentscope.csv

Install AgentScope

PyPIpip install agentscope

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Key facts

MakerAlibaba (Tongyi Lab)
TypeOpen-source multi-agent framework
First releasedJanuary 2024
LicenseApache-2.0
Main languagePython
Open issues and PRs613

Pricing

Free and open source (Apache-2.0).

Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.

Pulse Score breakdown

Adoption32
Community63
Attention—
Momentum53

Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.

AgentScope news and signals

All AI agent news

  1. New on AgentGid AgentGid

    101 agents added to AgentGid

    DeepSeek Harness, CopilotKit, Orca, eve, ARTEMIS, Jasper, Harvey, Paradox, Eightfold AI Interviewer, TesterArmy e2e, Copy.ai, Consensus and 89 more

  2. Release GitHub Releases

    AgentScope 2.0.9 released

    Standard Operating Procedures (Experimental): Added the agentscope.sop module for splitting a task into ordered milestones, each verified before the next one starts, with run state that can be…; Team Pipeline: Added a TeamPipeline class where a leader agent…

What changed: recent AgentScope releases

7 stable releases in the last 90 days · Full changelog

2.0.9
  • Standard Operating Procedures (Experimental): Added the agentscope.sop module for splitting a task into ordered milestones, each verified before the next one starts, with run state that can be…
  • Team Pipeline: Added a TeamPipeline class where a leader agent delegates tasks to member agents, which run concurrently and hand their results back.
  • More Realtime Voice Models: Added OpenAI Realtime, Gemini Live, and xAI Grok Voice models to the realtime voice agent.
  • Terminal UI: Introduced the agentscope.tui module, a full-screen terminal interface for chatting with agents and running realtime voice sessions via launchrealtimeui.
  • AskUser Tool: Added AskUser, an external tool that lets agents ask users multiple-choice questions.
  • MiniMax Model and Jev-based Model Routing: Added the MiniMax chat model (M3 by default), and a ModelRouterMiddleware backed by the new agentscope.classifier module (with Jev support) that picks…
2.0.8
  • Realtime Voice Agent: Introduced a realtime voice agent with DashScope backends and local transport support.
  • A2A Protocol Support: Added A2AAgent class to the agent module, enabling agent-to-agent communication.
  • New Pipeline Module: Added a new pipeline module with a GoalPipeline class for goal-driven agent workflows.
  • Agent-Driven Context Compression: Introduced a context compression tool that allows agents to manage their own context window.
  • LLM Rerank for RAG: Added LLM-based reranking support to improve RAG retrieval quality.
  • Volcengine Ark Model: Added support for Volcengine Ark chat model.
2.0.7.post1
  • fix(formatter): derive audio format from media type
  • fix(gemini): exclude tool-execution tokens from outputtokens
  • feat(formatter): use native multimodal tool outputs
  • docs(examples): fix broken relative link to types.py in mem0 README
  • feat(pipeline): add new pipeline module and a GoalPipeline class
  • fix(webui): isolate sessions when switching agents
2.0.7
  • fix(gemini): remove unsupported $schema from tool parameters
  • feat(workspace): share workspace across different agents
  • feat(workspace): isolate skills per agent, select them per session
  • fix(hub): preserve GitHub MCP environment inputs
  • fix(app): stop stranding session inbox payloads until the next user turn
  • feat(console): add terminal console for trying and debugging agents
2.0.6
  • Support channels (Feishu and Discord) in AgentScope (#1997)
  • Support Apple Container as workspace backend (#2068)
  • Support MCP & skill hubs/markets in agent service (#2197)
  • Add oncheckpermission middleware hook (#2001)
  • Refactor Web UI chat pages with shadcn (#2171)
  • feat(webui): refactor chat pages with shadcn and prepare for npm release
2.0.5
  • Support structured output (#2150)
  • Support environment information injection (#2134)
  • Support OpenSandbox (#1953), Daytona (#1943), K8s (#1933), Bubblewrap (#2051)
  • Support PowerShell for Windows (#2132)
  • Support MongoDB (#2008), Elasticsearch (#2129)
  • Support Excel (#2026) and Word (#2025) parser

AgentScope alternatives

All agent frameworks and SDKs

# Agent Pulse Downloads 7d 7d 30d VS Code installs Stars Latest release Price Last 90 days
4
LangChainLangChain
77 44.3M up 1.9% down 22.0% — 147K+45/day 1.4.38d ago Free (OSS)
10
LangGraphLangChain
69 16.1M up 11.4% down 21.8% — 42.7K+48/day 1.2.13yesterday Free (OSS)
11
AI SDKVercel
67 34.5M up 13.5% up 20.9% — 27.1K+18/day 6.0.301yesterday Free (OSS)
13 63 8.7M up 0.6% up 2.0% — 8,679+23/day 1.58.0yesterday Free (OSS)
18 59 21.5M up 14.6% up 0.6% — 8,219+5/day 0.2.1636d ago Free (OSS)
22
MastraMastra
58 2.2M up 11.1% up 19.1% — 28.6K+27/day 1.74.0yesterday Free (OSS)

AgentScope FAQ

How much does AgentScope cost?

Free and open source (Apache-2.0).

Is AgentScope open source?

Yes. AgentScope is open source, released under the Apache-2.0 license.

How popular is AgentScope?

AgentScope was downloaded 27.5K times from PyPI in the week ending Oct 4, 2026, up 18.6% on the week before. Its download count moved to a different level overnight on Sep 15, 2026. A jump like that comes from automated installs switching on or off or from a change in how the registry counts, so growth rates across that date are not shown. The GitHub repository has 32.8K stars, 2,053 of them added in the last 30 days.

What is the latest version of AgentScope?

The latest stable release we track is 2.0.9, published on Sep 28, 2026.

What are the alternatives to AgentScope?

The closest alternatives in the same category by Pulse Score are LangChain, LangGraph, AI SDK, Strands Agents.

Where these numbers come from

PyPI: agentscope. GitHub: agentscope-ai/agentscope. Site rank: agentscope.io on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: github.com, pypi.org.