hub / github.com/modelscope/ms-agent

github.com/modelscope/ms-agent @v1.6.0

repository ↗ · DeepWiki ↗ · release v1.6.0 ↗ · Ask this repo → · + Follow

2,502 symbols 9,389 edges 275 files 1,329 documented · 53% ● updated 2d agov1.6.0 · 2026-03-23★ 4,33111 open issues

README

MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration

<img src="https://modelscope.oss-cn-beijing.aliyuncs.com/modelscope.gif" width="400"/>

MCP Playground | Paper | Documentation | 中文文档

中文

Introduction

MS-Agent is a lightweight framework designed to empower agents with autonomous exploration capabilities. It provides a flexible and extensible architecture that allows developers to create agents capable of performing complex tasks, such as code generation, data analysis, and tool calling for general purposes with MCP (Model Calling Protocol) support.

Features

Multi-Agent for general purpose: Chat with agent with tool-calling capabilities based on MCP.
Deep Research: To enable advanced capabilities for autonomous exploration and complex task execution.
Code Generation: Supports code generation tasks with artifacts.
Short Video Generation：Support video generation of about 5 minutes.
Agent Skills: Implementation of Anthropic-Agent-Skills Protocol.
WebUI: Modern web interface for agent interaction with real-time WebSocket communication.
Lightweight and Extensible: Easy to extend and customize for various applications.

[WARNING] For historical archive versions, please refer to: https://github.com/modelscope/ms-agent/tree/0.8.0

WeChat Group

🎉 News

🚀 Mar 23, 2026: Release MS-Agent v1.6.0, which includes the following updates:
Context Compression: Added context compression mechanism with token usage monitoring, overflow detection, and automatic context compaction via pruning historical tool outputs and LLM-based summarization.
Agentic Insight v2 Enhancements: Major architecture and performance improvements to the deep research system; achieves 55.43 on DeepResearch Bench with GPT5 and Qwen3.5-plus/flash. See Agentic Insight v2.
Knowledge Search: Integrated Sirchmunk for intelligent retrieval over local codebases and documentation during agent conversations. See Config Docs.
Multimodal Model Input: Support image, video, and other multimodal inputs. See Multimodal Docs.
🚀 Feb 06, 2026: Release MS-Agent v1.6.0rc1, which includes the following updates:
Agentic Insight v2: A fully refactored deep-research system with better performance, scalability, and trustworthiness, now available in WebUI. See Agentic Insight v2.
🚀 Feb 04, 2026: Release MS-Agent v1.6.0rc0, which includes the following updates:
Code Genesis for complex code generation tasks, refer to Code Genesis
Singularity Cinema for animated video generation workflow, refactored version, refer to Singularity Cinema
New framework of Skills: New design of the skills system to enhance robustness and extensibility. Refer to MS-Agent Skills.
WebUI: A new WebUI has been added, featuring agentic chatting capabilities, complex code generation and video generation workflow.
🎬 Nov 13, 2025: Release Singularity Cinema, to support short video generation for complex scenarios, check here
🚀 Nov 12, 2025: Release MS-Agent v1.5.0, which includes the following updates:
🔥 We present FinResearch, a multi-agent workflow tailored for financial research
Support financial data collection via Akshare and Baostock
Support DagWorkflow for workflow orchestration
Optimize the DeepResearch workflow for stability and efficiency
FinResearch official documentation: FinResearch Doc
DEMO: FinResearchStudio
Examples: FinResearchExamples
🚀 Nov 07, 2025: Release MS-Agent v1.4.0, which includes the following updates:
🔥 We present MS-Agent Skills, an Implementation of Anthropic-Agent-Skills Protocol.
🔥 Add Docs and 中文文档
🔥 Support Sandbox Framework ms-enclave
🚀 Sep 22, 2025: Release MS-Agent v1.3.0, which includes the following updates:
🔥 Support Code Scratch
Support Memory for building agents with long-term and short-term memory
Enhance the DeepResearch workflow
Support RAY for accelerating document information extraction
Support Anthropic API format for LLMs
🚀 Aug 28, 2025: Release MS-Agent v1.2.0, which includes the following updates:
DocResearch now supports pushing to ModelScope、HuggingFace、GitHub for easy sharing of research reports. Refer to Doc Research for more details.
DocResearch now supports exporting the Markdown report to HTML、PDF、PPTX and DOCX formats, refer to Doc Research for more details.
DocResearch now supports TXT file processing and file preprocessing, refer to Doc Research for more details.

Installation

Install from PyPI

# For the basic functionalities
pip install ms-agent

# For the deep research functionalities
pip install 'ms-agent[research]'

Install from source

git clone https://github.com/modelscope/ms-agent.git

cd ms-agent
pip install -e .

[!WARNING] As the project has been renamed to ms-agent, for versions v0.8.0 or earlier, you can install using the following command:

Extension points exported contracts — how you extend this code

MessageContentProps (Interface)

(no doc)

webui/frontend/src/components/MessageContent.tsx

LayoutProps (Interface)

(no doc)

webui/frontend/src/components/Layout.tsx

ConversationViewProps (Interface)

(no doc)

webui/frontend/src/components/ConversationView.tsx

MessageBubbleProps (Interface)

(no doc)

webui/frontend/src/components/ConversationView.tsx

WorkflowViewProps (Interface)

(no doc)

webui/frontend/src/components/ConversationView.tsx

Core symbols most depended-on inside this repo

get

called by 1097

ms_agent/memory/default_memory.py

get_logger

called by 79

ms_agent/utils/logger.py

write

called by 78

webui/backend/deep_research_worker.py

parse_imports

called by 62

ms_agent/utils/parser_utils.py

load

called by 61

ms_agent/tools/docling/doc_loader.py

called by 51

ms_agent/tools/search/exa/search.py

add

called by 49

ms_agent/memory/default_memory.py

resolve

called by 47

ms_agent/app/fin_research.py

Shape

Method 1,692

Function 425

Class 316

Route 35

Interface 34

Languages

Python96%

TypeScript4%

Modules by API surface

ms_agent/app/fin_research.py83 symbols

webui/backend/api.py80 symbols

tests/utils/test_parse_imports.py77 symbols

ms_agent/skill/auto_skills.py60 symbols

ms_agent/agent/llm_agent.py52 symbols

examples/skills/claude_skills/docx/scripts/document.py52 symbols

tests/skills/test_claude_skills.py49 symbols

ms_agent/skill/container.py49 symbols

ms_agent/app/doc_research.py45 symbols

ms_agent/utils/parser_utils.py40 symbols

projects/deep_research/v2/tools/evidence_tool.py38 symbols

ms_agent/tools/agent_tool.py38 symbols

Dependencies from manifests, versioned

@emotion/react11.11.3 · 1×

@emotion/styled11.11.0 · 1×

@mui/icons-material5.15.6 · 1×

@mui/material5.15.6 · 1×

@types/react18.2.48 · 1×

@types/react-dom18.2.18 · 1×

@types/react-syntax-highlighter15.5.11 · 1×

@vitejs/plugin-react4.2.1 · 1×

framer-motion11.0.3 · 1×

react18.2.0 · 1×

react-dom18.2.0 · 1×

react-markdown9.0.1 · 1×

Datastores touched

mydbDatabase · 1 repos

For agents

$ claude mcp add ms-agent \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact