---
title: "agent-framework vs zcf"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/microsoft-agent-framework-vs-ufomiao-zcf"
tools: ["microsoft-agent-framework", "ufomiao-zcf"]
---

# agent-framework vs zcf

*GraphCanon updated Sep 20, 2026*

## Verdict

Pick agent-framework if the agent-framework provides tools for developers to build and deploy AI agents and multi-agent workflows in Python and .NET environments; pick zcf if zcf offers specialized support for AI-assisted coding with Claude code and Codex via an easy-to-use CLI. It focuses on minimizing initial setup through interactive menus and non-interactive command-line options.

[agent-framework](https://aka.ms/agent-framework) reports 14k GitHub stars, 2.3k forks, and 605 open issues, last pushed Sep 18, 2026. [zcf](http://zcf.ufomiao.com/) has 6.1k stars, 420 forks, and 42 open issues, last pushed Aug 31, 2026. Figures are from public GitHub metadata via [agent-framework's repository](https://github.com/microsoft/agent-framework) and [zcf's repository](https://github.com/UfoMiao/zcf).

| | [agent-framework](/tools/microsoft-agent-framework.md) | [zcf](/tools/ufomiao-zcf.md) |
| --- | --- | --- |
| Tagline | Framework for building and deploying AI agents and multi-agent workflows | Zero-Config Code Flow for Claude code & Codex |
| Stars | 13,573 | 6,083 |
| Forks | 2,335 | 420 |
| Open issues | 605 | 42 |
| Language | Python | TypeScript |
| Adopt for | The agent-framework provides tools for developers to build and deploy AI agents and multi-agent workflows in Python and .NET environments. | zcf offers specialized support for AI-assisted coding with Claude code and Codex via an easy-to-use CLI. It focuses on minimizing initial setup through interactive menus and non-interactive command-line options. |
| Persona | - | - |
| Runtime | - | - |
| License | MIT | MIT |
| Categories | AI Agents, Developer Tools | AI Agents, Developer Tools |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [agent-framework](/tools/microsoft-agent-framework.md) | [zcf](/tools/ufomiao-zcf.md) |
| --- | --- | --- |
| Maintenance | Very active (96%) | Active (82%) |
| Days since push | 0d | 15d |
| Open issues (now) | 605 | 42 |
| Stars delta | +855 (30d) | +6 (30d) |
| Open issues delta | -80 (30d) | -5 (30d) |
| Full report | [trust report](/tools/microsoft-agent-framework/trust.md) | [trust report](/tools/ufomiao-zcf/trust.md) |

## Decision facts: agent-framework

- **Requirements:** Python version 3.6 or newer is required for Python installations.; The .NET Core SDK must be installed for utilizing the .NET packages.
- **Adopt for:** The agent-framework provides tools for developers to build and deploy AI agents and multi-agent workflows in Python and .NET environments.

## Decision facts: zcf

- **Adopt for:** zcf offers specialized support for AI-assisted coding with Claude code and Codex via an easy-to-use CLI. It focuses on minimizing initial setup through interactive menus and non-interactive command-line options.

## Choose when

### Choose agent-framework if…

- agent-framework is primarily Python; zcf is TypeScript.
- Requirements: Python version 3.6 or newer is required for Python installations.; The .NET Core SDK must be installed for utilizing the .NET packages..
- Tags unique to agent-framework: agent-framework, agentic-ai, agents, multi-agent.
- Choose agent-framework if your project requires support for both Python and .NET, allowing you to develop across different ecosystems.

### Choose zcf if…

- zcf is primarily TypeScript; agent-framework is Python.
- Tags unique to zcf: agent, ai-agent, bmad-method, ccr.
- If you need a tool that simplifies workflow initialization specifically tailored to Claude code or Codex models, especially within TypeScript environments.

## When NOT to use agent-framework

- Avoid using the agent-framework if your team does not have proficiency in either Python or.NET, as this may cause difficulties in leveraging its features effectively.
- Do not opt for agent-framework if you only need lightweight support for AI agents without a comprehensive orchestration and deployment framework.

## When NOT to use zcf

- Avoid using zcf if your team is not comfortable working in a TypeScript setup or if Claude code and Codex are not the preferred language models for your project.
- If you require deep customization beyond what presets and common commands offer, and need more granular control over AI integration processes that are not provided by this CLI.

## Common questions

### What is the difference between agent-framework and zcf?

agent-framework: Framework for building and deploying AI agents and multi-agent workflows. zcf: Zero-Config Code Flow for Claude code & Codex. See the comparison table for live GitHub stats and shared categories.

### When should I choose agent-framework over zcf?

Choose agent-framework over zcf when agent-framework is primarily Python; zcf is TypeScript; Requirements: Python version 3.6 or newer is required for Python installations.; The .NET Core SDK must be installed for utilizing the .NET packages.; Tags unique to agent-framework: agent-framework, agentic-ai, agents, multi-agent; Choose agent-framework if your project requires support for both Python and .NET, allowing you to develop across different ecosystems.

### When should I choose zcf over agent-framework?

Choose zcf over agent-framework when zcf is primarily TypeScript; agent-framework is Python; Tags unique to zcf: agent, ai-agent, bmad-method, ccr; If you need a tool that simplifies workflow initialization specifically tailored to Claude code or Codex models, especially within TypeScript environments.

### When should I avoid agent-framework?

Avoid using the agent-framework if your team does not have proficiency in either Python or.NET, as this may cause difficulties in leveraging its features effectively. Do not opt for agent-framework if you only need lightweight support for AI agents without a comprehensive orchestration and deployment framework.

### When should I avoid zcf?

Avoid using zcf if your team is not comfortable working in a TypeScript setup or if Claude code and Codex are not the preferred language models for your project. If you require deep customization beyond what presets and common commands offer, and need more granular control over AI integration processes that are not provided by this CLI.

### Is agent-framework or zcf more popular on GitHub?

agent-framework has more GitHub stars (13,573 vs 6,083). Stars measure visibility, not whether either tool fits your constraints.

### Are agent-framework and zcf open source?

Yes - both are open-source projects on GitHub (agent-framework: MIT, zcf: MIT).

### Where can I find alternatives to agent-framework or zcf?

GraphCanon lists graph-backed alternatives at [agent-framework alternatives](/tools/microsoft-agent-framework/alternatives) and [zcf alternatives](/tools/ufomiao-zcf/alternatives) ([agent-framework markdown twin](/tools/microsoft-agent-framework/alternatives.md), [zcf markdown twin](/tools/ufomiao-zcf/alternatives.md)), ranked by typed relationship edges rather than popularity votes.

### Is there a machine-readable version of this comparison?

Yes. The markdown twin at [this comparison](/compare/microsoft-agent-framework-vs-ufomiao-zcf.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, agent-framework or zcf?

agent-framework: Very active. zcf: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.

### Where are the full trust reports for agent-framework and zcf?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-framework trust report](/tools/microsoft-agent-framework/trust); [zcf trust report](/tools/ufomiao-zcf/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=microsoft-agent-framework`](/api/graphcanon/graph?tool=microsoft-agent-framework)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_
