--- title: "agent-framework vs onyx" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-agent-framework-vs-onyx-dot-app-onyx" tools: ["microsoft-agent-framework", "onyx-dot-app-onyx"] --- # agent-framework vs onyx *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 onyx if onyx is an open-source AI platform that supports AI chat functionalities with advanced features, suitable for deployment in various environments including Docker, Kubernetes, and cloud providers. It offers both Lite and,. [agent-framework](https://aka.ms/agent-framework) reports 14k GitHub stars, 2.3k forks, and 605 open issues, last pushed Sep 18, 2026. [onyx](https://onyx.app) has 32k stars, 4.5k forks, and 470 open issues, last pushed Sep 18, 2026. Figures are from public GitHub metadata via [agent-framework's repository](https://github.com/microsoft/agent-framework) and [onyx's repository](https://github.com/onyx-dot-app/onyx). | | [agent-framework](/tools/microsoft-agent-framework.md) | [onyx](/tools/onyx-dot-app-onyx.md) | | --- | --- | --- | | Tagline | Framework for building and deploying AI agents and multi-agent workflows | Open Source AI Platform - AI Chat with advanced features that works with every LLM | | Stars | 13,573 | 32,153 | | Forks | 2,335 | 4,477 | | Open issues | 605 | 470 | | Language | Python | Python | | Adopt for | The agent-framework provides tools for developers to build and deploy AI agents and multi-agent workflows in Python and .NET environments. | Onyx is an open-source AI platform that supports AI chat functionalities with advanced features, suitable for deployment in various environments including Docker, Kubernetes, and cloud providers. It offers both Lite and, | | Persona | - | - | | Runtime | - | - | | License | MIT | Onyx is available in two editions: Community Edition (CE) under the MIT license, which covers core features, and Enterprise Edition (EE) with additional features for larger organizations. | | Categories | AI Agents, Developer Tools | AI Agents, Data & Retrieval, Developer Tools, Inference & Serving, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-framework](/tools/microsoft-agent-framework.md) | [onyx](/tools/onyx-dot-app-onyx.md) | | --- | --- | --- | | Open issues (now) | 605 | 470 | | Stars delta | +855 (30d) | +536 (30d) | | Open issues delta | -80 (30d) | +69 (30d) | | Full report | [trust report](/tools/microsoft-agent-framework/trust.md) | [trust report](/tools/onyx-dot-app-onyx/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: onyx - **Pricing:** freemium - Onyx Community Edition is free under the MIT license, while the Enterprise Edition includes extra features for larger organizations and requires a paid subscription. - **Requirements:** Min 1 GB RAM; Lite mode requires under 1GB of memory, while Standard mode requires more resources for its additional features. - **Adopt for:** Onyx is an open-source AI platform that supports AI chat functionalities with advanced features, suitable for deployment in various environments including Docker, Kubernetes, and cloud providers. It offers both Lite and, - **License detail:** Onyx is available in two editions: Community Edition (CE) under the MIT license, which covers core features, and Enterprise Edition (EE) with additional features for larger organizations. ## Choose when ### Choose agent-framework if… - License: agent-framework is MIT, onyx is Other. - 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 onyx if… - License: onyx is Other, agent-framework is MIT. - Pricing: Onyx Community Edition is free under the MIT license, while the Enterprise Edition includes extra features for larger organizations and requires a paid subscription.. - Requirements: Min 1 GB RAM; Lite mode requires under 1GB of memory, while Standard mode requires more resources for its additional features.. - Tags unique to onyx: ai-chat, chatui, enterprise-search, gen-ai. - Also covers Data & Retrieval, Inference & Serving, Model Training. - use Onyx when you need a platform that supports both lightweight and full-featured deployments, including vector and keyword indexing, and performance optimizations for large-scale use. ## 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 onyx - avoid Onyx if you are looking for a platform that requires minimal setup and resource usage beyond what the Lite mode offers. - do not use Onyx if your project does not benefit from vector and keyword indexing, AI model inference servers, or performance optimizations, as these features are only available in the Standard mode. ## Common questions ### What is the difference between agent-framework and onyx? agent-framework: Framework for building and deploying AI agents and multi-agent workflows. onyx: Open Source AI Platform - AI Chat with advanced features that works with every LLM. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-framework over onyx? Choose agent-framework over onyx when License: agent-framework is MIT, onyx is Other; 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 onyx over agent-framework? Choose onyx over agent-framework when License: onyx is Other, agent-framework is MIT; Pricing: Onyx Community Edition is free under the MIT license, while the Enterprise Edition includes extra features for larger organizations and requires a paid subscription.; Requirements: Min 1 GB RAM; Lite mode requires under 1GB of memory, while Standard mode requires more resources for its additional features.; Tags unique to onyx: ai-chat, chatui, enterprise-search, gen-ai; Also covers Data & Retrieval, Inference & Serving, Model Training; use Onyx when you need a platform that supports both lightweight and full-featured deployments, including vector and keyword indexing, and performance optimizations for large-scale use. ### 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 onyx? avoid Onyx if you are looking for a platform that requires minimal setup and resource usage beyond what the Lite mode offers. do not use Onyx if your project does not benefit from vector and keyword indexing, AI model inference servers, or performance optimizations, as these features are only available in the Standard mode. ### Is agent-framework or onyx more popular on GitHub? onyx has more GitHub stars (32,153 vs 13,573). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-framework and onyx open source? Yes - both are open-source projects on GitHub (agent-framework: MIT, onyx: Other). ### Where can I find alternatives to agent-framework or onyx? GraphCanon lists graph-backed alternatives at [agent-framework alternatives](/tools/microsoft-agent-framework/alternatives) and [onyx alternatives](/tools/onyx-dot-app-onyx/alternatives) ([agent-framework markdown twin](/tools/microsoft-agent-framework/alternatives.md), [onyx markdown twin](/tools/onyx-dot-app-onyx/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-onyx-dot-app-onyx.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-framework or onyx? agent-framework: Very active. onyx: 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 onyx? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-framework trust report](/tools/microsoft-agent-framework/trust); [onyx trust report](/tools/onyx-dot-app-onyx/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/_