modelscope/ms-agent

MS-Agent: a lightweight framework to empower agentic execution of complex tasks

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 58 minutes ago
Added to GitGenius on September 15th, 2026
Created on August 3rd, 2023
Open Issues & Pull Requests: 31 (+0)
GitHub issues: Enabled
Number of forks: 521
Total Stargazers: 4,391 (+1)
Total Subscribers: 49 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 0.0 hours
Mean response time: 7.3 days
90th percentile: 5.2 days
Tracked items: 95

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Work labelled "enhancement" is answered fastest, typically in under an hour, while "llm" waits about 2 days. Three people close 89% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 11
New in 7 days: 1
Closed in 7 days: 1
Avg open age: 186 days
Stale 30+ days: 10
Stale 90+ days: 10

Recent activity

Opened in 7 days: 0
Closed in 7 days: 1
Comments in 7 days: 1
Events in 7 days: 2

Top labels

  • bug (39)
  • enhancement (24)
  • llm (11)
  • tool (6)
  • question (4)
  • framework (3)
  • help wanted (3)
  • legacy (3)

Most active issues this week

Detailed Description

MS-Agent is a lightweight framework for building agents that execute complex tasks autonomously.

The framework addresses the challenge of orchestrating multi-step reasoning and tool use in agentic systems. It provides abstractions for defining agents that can decompose complex problems, maintain memory across interactions, and coordinate the use of external tools and APIs. The approach centers on enabling flexible agent architectures where reasoning, planning, and execution can be composed together without requiring heavy dependencies.

Teams building chatbots, code generation systems, or research automation tools should consider this framework. It suits projects where agents need to perform deep research, generate code, or conduct agentic search across information sources. The lightweight nature makes it appropriate for scenarios where minimal overhead is desired compared to heavier agent frameworks.

Development activity shows consistent engagement with the codebase through regular commits and pull request reviews. The project maintains active documentation and responds to issues raised by users. Contributions are reviewed before merging, indicating a structured approach to code quality. The maintainers have established a documented API surface and examples that guide adoption.