MS-Agent
Lightweight Python agent framework for long-running tasks, with skills, sub-agents, A2A and ACP servers, and CLI, TUI and web front ends.
Harness by ModelScope
Chalk Labs
Need help deploying MS-Agent?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
From the package registry. Read the repository before you give any tool access to your data.
pip install ms-agent
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-orchestration
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Languages
- PythonREADME
- Packages
- ms-agent (pypi)README
- Multi-agent
- YesREADME
- Orchestration
- sequentialms-agent-en.readthedocs.io
- A2A support
- Built inms-agent-en.readthedocs.io
- Agent Skills support
- Built inms-agent-en.readthedocs.io
- Model providers
- openai, anthropic, modelscopems-agent-en.readthedocs.io
- Maturity
- StableREADME
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Alternatives
Frameworks for the same language with a similar way of orchestrating agents.
- 0.752score
PraisonAI
Mervin Praison
Python framework for multi-agent teams and workflows, with a CLI and Docker, MCP and A2A deployment options.
HarnessAFreshness: A★ 9.3K↓ 4.6K/wk - 0.732score
CrewAI
CrewAI
Open-source Python framework for multi-agent workflows, with role-based Crews and event-driven Flows.
HarnessAFreshness: A★ 60.1K↓ 644.6K/wk - 0.648score
Atomic Agents
Eigenwise
Lightweight Python framework for composing AI agents and tools as small, typed pieces built on Instructor and Pydantic.
HarnessAFreshness: A★ 6.3K↓ 4.6K/wk - 0.642score
Swarms
Swarms
Python framework for orchestrating multiple LLM agents in sequential, concurrent, hierarchical and graph-based workflows.
HarnessAFreshness: A★ 7.3K↓ 3.3K/wk - 0.607score
Microsoft Agent Framework
Microsoft
Open framework for building and hosting production-grade AI agents and multi-agent workflows in .NET and Python.
HarnessAFreshness: A★ 14.3K↓ 47.6K/wk
Signals
- Stars
- 4,417
- Forks
- 533
- Open issues
- 15
- Weekly downloads
- 107
- Last commit
- Oct 19, 2026 (12 days ago)
- Last release
- Mar 23, 2026 (7 months ago)
- Last package publish
- Mar 23, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Packages
- pypi
ms-agent - License
- Apache-2.0
- Repository
- github.com/modelscope/ms-agent
- Website
- ms-agent-en.readthedocs.io
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEDocsgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get MS-Agent running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
MS-Agent. Agent Mart. https://agentmart.dev/harnesses/ms-agent (last updated 2026-10-24)