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

# agent-framework vs manifest

*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 manifest if manifest is a TypeScript framework under MIT license that enables integration of AI agents across various providers, with an emphasis on observability and tracking mechanisms such as token and cost-tracking.

[agent-framework](https://aka.ms/agent-framework) reports 14k GitHub stars, 2.3k forks, and 605 open issues, last pushed Sep 18, 2026. [manifest](https://manifest.build) has 7.5k stars, 508 forks, and 110 open issues, last pushed Sep 10, 2026. Figures are from public GitHub metadata via [agent-framework's repository](https://github.com/microsoft/agent-framework) and [manifest's repository](https://github.com/mnfst/manifest).

| | [agent-framework](/tools/microsoft-agent-framework.md) | [manifest](/tools/mnfst-manifest.md) |
| --- | --- | --- |
| Tagline | Framework for building and deploying AI agents and multi-agent workflows | Connect Your Agents And Harnesses With Any Provider |
| Stars | 13,573 | 7,514 |
| Forks | 2,335 | 508 |
| Open issues | 605 | 110 |
| 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. | Manifest is a TypeScript framework under MIT license that enables integration of AI agents across various providers, with an emphasis on observability and tracking mechanisms such as token and cost-tracking. |
| Persona | - | - |
| Runtime | - | - |
| License | MIT | MIT |
| Categories | AI Agents, Developer Tools | AI Agents, Evaluation & Observability |

## Trust and health

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

| | [agent-framework](/tools/microsoft-agent-framework.md) | [manifest](/tools/mnfst-manifest.md) |
| --- | --- | --- |
| Open issues (now) | 605 | 110 |
| Stars delta | +855 (30d) | +100 (30d) |
| Open issues delta | -80 (30d) | +1 (30d) |
| Full report | [trust report](/tools/microsoft-agent-framework/trust.md) | [trust report](/tools/mnfst-manifest/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: manifest

- **Adopt for:** Manifest is a TypeScript framework under MIT license that enables integration of AI agents across various providers, with an emphasis on observability and tracking mechanisms such as token and cost-tracking.

## Choose when

### Choose agent-framework if…

- agent-framework is primarily Python; manifest 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.
- Also covers Developer Tools.
- Choose agent-framework if your project requires support for both Python and .NET, allowing you to develop across different ecosystems.

### Choose manifest if…

- manifest is primarily TypeScript; agent-framework is Python.
- Tags unique to manifest: ai-agents, llm-observability.
- Also covers Evaluation & Observability.
- When you need to establish connections between multiple AI providers without altering the core functionality or architecture of your existing systems.

## 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 manifest

- If your project strictly requires use cases with non-TypeScript languages, as this would necessitate additional integration work.
- When you require a mature framework; given Manifest's beta status, it might not be the best choice for production environments sensitive to potential bugs or incomplete features.

## Common questions

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

agent-framework: Framework for building and deploying AI agents and multi-agent workflows. manifest: Connect Your Agents And Harnesses With Any Provider. See the comparison table for live GitHub stats and shared categories.

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

Choose agent-framework over manifest when agent-framework is primarily Python; manifest 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; Also covers Developer Tools; Choose agent-framework if your project requires support for both Python and .NET, allowing you to develop across different ecosystems.

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

Choose manifest over agent-framework when manifest is primarily TypeScript; agent-framework is Python; Tags unique to manifest: ai-agents, llm-observability; Also covers Evaluation & Observability; When you need to establish connections between multiple AI providers without altering the core functionality or architecture of your existing systems.

### 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 manifest?

If your project strictly requires use cases with non-TypeScript languages, as this would necessitate additional integration work. When you require a mature framework; given Manifest's beta status, it might not be the best choice for production environments sensitive to potential bugs or incomplete features.

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

agent-framework has more GitHub stars (13,573 vs 7,514). Stars measure visibility, not whether either tool fits your constraints.

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

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

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

GraphCanon lists graph-backed alternatives at [agent-framework alternatives](/tools/microsoft-agent-framework/alternatives) and [manifest alternatives](/tools/mnfst-manifest/alternatives) ([agent-framework markdown twin](/tools/microsoft-agent-framework/alternatives.md), [manifest markdown twin](/tools/mnfst-manifest/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-mnfst-manifest.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

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

agent-framework: Very active. manifest: Very 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 manifest?

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