Skip to main content
ClaudeWave
EN, English
agentscope-ai / Subagents

agentscope

Build and run agents you can see, understand and trust.

  • 33.7k stars
  • 3.7k forks
  • 660 open issues
  • Language: Python
  • License: Apache-2.0
  • updated
Install in ClaudeView on GitHub

Install

Terminal
git clone https://github.com/agentscope-ai/agentscope && cp agentscope/*.md ~/.claude/agents/
  1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
  2. Start a new Claude Code session to load the agents.
  3. Delegate work to them with the Task/Agent tool or by name.

Editor's note

AgentScope is a Python framework for building and deploying LLM-based agents, with version 2.0 targeting production environments through multi-tenancy, multi-session service isolation, and workspace sandboxing backed by local, Docker, or E2B runtimes. Agents are constructed with a Toolkit abstraction that includes built-in tools such as Bash, Grep, Glob, Read, Write, and Edit, and the framework exposes a streaming event bus covering lifecycle events like REPLY_START, MODEL_CALL_START, and TEXT_BLOCK_DELTA, enabling real-time frontend updates and human-in-the-loop workflows. A permission system provides fine-grained control over which tools and resources an agent can access, while a composable middleware system allows developers to hook into the reasoning-acting loop. The framework connects to LLMs through model adapters, including DashScopeChatModel, and carries MCP compatibility for broader tool ecosystems. Developers building multi-agent pipelines, SaaS platforms, or coding assistants who need observable, tenant-isolated agent infrastructure will find it most useful. The recently added Agent Team feature extends coordination to grouped agent setups.

README

Subagents overview

Full README on GitHub

src="https://img.alicdn.com/imgextra/i1/O1CN01nTg6w21NqT5qFKH1u_!!6000000001621-55-tps-550-550.svg" alt="AgentScope Logo" width="200" />

中文主页 | Documentation | Roadmap

src="https://img.shields.io/badge/cs.MA-2402.14034-B31C1C?logo=arxiv&logoColor=B31C1C" alt="arxiv" /> src="https://img.shields.io/badge/python-3.11+-blue?logo=python" alt="pypi" /> src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fpypi.org%2Fpypi%2Fagentscope%2Fjson&query=%24.info.version&prefix=v&logo=pypi&label=version" alt="pypi" /> src="https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white" alt="discord" /> src="https://img.shields.io/badge/Docs-English%7C%E4%B8%AD%E6%96%87-blue?logo=markdown" alt="docs" /> src="https://img.shields.io/badge/license-Apache--2.0-black" alt="license" /> src="https://img.shields.io/badge/DeepWiki-Ask_Devin-navy.svg?logo=data:image/png;base64,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)" alt="Ask DeepWiki" />

What is AgentScope 2.0?

AgentScope 2.0 is a production-ready, easy-to-use agent framework with essential abstractions that keep up with rising model capability.

We design for increasingly agentic LLMs. Our approach leverages the models' reasoning and tool use abilities rather than constraining them with strict prompts and opinionated orchestrations.

News

  • [2026-10] FEAT Experimental: Agent service supports realtime voice conversations over WebRTC, with text and voice sharing the same session history.

  • [2026-09] FEAT Experimental: SOP supported — run multi-step tasks as standard operating procedures, in both the framework and agent service. Docs | Service

  • [2026-09] FEAT: TeamPipeline supported — a leader agent delegates tasks to member agents. Docs

  • [2026-09] INTE: MiniMax chat models supported via MiniMaxChatModel (MiniMax-M3 by default).

  • [2026-09] FEAT: Model routing supported — use ModelRouterMiddleware to select an appropriate chat model for each reply.

  • [2026-09] INTE: Jev classifier model supported through the TypeSafe SDK via JevClassifierModel.

  • [2026-09] FEAT: agentscope-skill now supports AgentScope v2.

  • [2026-09] INTE: Support DashScope, OpenAI, Gemini and xAI realtime APIs in RealtimeAgent. Example | Docs

  • [2026-09] FEAT Experimental: Realtime voice agent supported. Example | Docs

  • [2026-09] FEAT: A2A protocol supported — chat with any remote A2A agent via A2AAgent. Example | Docs

More news →

Community

Welcome to join our community on

DiscordDingTalk

Quickstart

Installation

AgentScope requires Python 3.11 or higher.

From PyPI
uv pip install agentscope
From source
# Pull the source code from GitHub
git clone -b main https://github.com/agentscope-ai/agentscope.git

# Install the package in editable mode
cd agentscope

uv pip install -e .

Agent

The SDK layer — compose an agent from a rich set of building blocks:

Building blockWhat's inside
ReActReasoning-acting loop with structured output, realtime interruption & resume, and batched (sequential / concurrent) tool acting
ToolkitAgentic tool management over Python tools, MCP servers, and skills; ships with built-in coding tools (shell, file edit, search) and task/plan tools
ModelLLM, embedding, and TTS across major providers (OpenAI, Anthropic, Gemini, DashScope, DeepSeek, Moonshot, Volcengine, xAI, Ollama)
ContextAutomatic compaction, tool-result offload, and context injection (system prompt, RAG, memory) via built-in middleware
Event SystemUnified event bus streaming reasoning, tool calls, and multimodal content (text, image, audio) to the frontend
Permission & HITLFine-grained control over tools and resources, confirmation, bypass mode
MiddlewareComposable hooks across the loop — reply, reasoning, acting, model calling, permission checking, context compression, system prompt
MemoryAgentic memory with switchable backends (ReMe, Mem0)
Workspace / SandboxIsolated tool & code execution — local, Docker, Apple Container, Bubblewrap, E2B, OpenSandbox, Daytona, K8s

Start your first agent with AgentScope 2.0 in console:

from agentscope.agent import Agent
from agentscope.console import launch_console
from agentscope.tool import Toolkit, Bash, Grep, Glob, Read, Write, Edit
from agentscope.credential import DashScopeCredential
from agentscope.model import DashScopeChatModel

import os, asyncio


async def main() -> None:
    agent = Agent(
        name="Friday",
        system_prompt="You're a helpful assistant named Friday.",
        model=DashScopeChatModel(
            credential=DashScopeCredential(
              api_key=os.environ["DASHSCOPE_API_KEY"]
            ),
            model="qwen3.6-plus",
        ),
        toolkit=Toolkit(
            tools=[
                Bash(),
                Grep(),
                Glob(),
                Read(),
                Write(),
                Edit(),
            ]
        ),
    )

    # Chat with the agent in the terminal — streamed output, tool-call
    # confirmation and Ctrl+C interruption are all handled for you
    await launch_console(agent)

asyncio.run(main())

Agent Service — All You Need to Build Your App

Use cases
Creative Dev Tools Social
Topics
agentchatbotlarge-language-modelsllmllm-agentmcpmulti-agentmulti-modalreact-agentrealtime-agentvoice-agentvoice-assistant
Frequently asked

What people ask about agentscope

What is agentscope-ai/agentscope?

agentscope-ai/agentscope is subagents for the Claude AI ecosystem. Build and run agents you can see, understand and trust. It has 33.7k GitHub stars and its last recorded update is dated 2026-10-23.

How do I install agentscope?

You can install agentscope by cloning the repository (https://github.com/agentscope-ai/agentscope) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is agentscope-ai/agentscope safe to use?

Our security agent has analyzed agentscope-ai/agentscope and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains agentscope-ai/agentscope?

agentscope-ai/agentscope is maintained by agentscope-ai. The last recorded GitHub activity is dated 2026-10-23, with 660 open issues.

Are there alternatives to agentscope?

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.

Trust Score badge

Maintain this repo? Show its Trust Score in your README

The badge shows this repository's current Trust Score and verdict, and links back to this page. It follows the catalogue data: nobody can buy or edit the score it displays.

ClaudeWave Trust Score for agentscope-ai/agentscope
Markdown (README)
[![ClaudeWave Trust Score for agentscope-ai/agentscope](https://claudewave.com/api/badge/agentscope-ai-agentscope)](https://claudewave.com/en/repo/agentscope-ai-agentscope)
HTML
<a href="https://claudewave.com/en/repo/agentscope-ai-agentscope"><img src="https://claudewave.com/api/badge/agentscope-ai-agentscope" alt="ClaudeWave Trust Score for agentscope-ai/agentscope" width="320" height="64"></a>

What the badge means and how the score is computed

Alternatives

Project homepage
https://docs.agentscope.io/