--- title: "agent-framework vs agents-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-agent-framework-vs-pguso-agents-from-scratch" tools: ["microsoft-agent-framework", "pguso-agents-from-scratch"] --- # agent-framework vs agents-from-scratch *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 agents-from-scratch if agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. [agent-framework](https://aka.ms/agent-framework) reports 14k GitHub stars, 2.3k forks, and 605 open issues, last pushed Sep 18, 2026. [agents-from-scratch](https://github.com/pguso/agents-from-scratch) has 1.0k stars, 251 forks, and 4 open issues, last pushed Jul 25, 2026. Figures are from public GitHub metadata via [agent-framework's repository](https://github.com/microsoft/agent-framework) and [agents-from-scratch's repository](https://github.com/pguso/agents-from-scratch). | | [agent-framework](/tools/microsoft-agent-framework.md) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Tagline | Framework for building and deploying AI agents and multi-agent workflows | Build AI agents locally without relying on frameworks or cloud APIs. | | Stars | 13,573 | 1,017 | | Forks | 2,335 | 251 | | Open issues | 605 | 4 | | 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. | agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. | | 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) | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Steady (60%) | | Days since push | 0d | 56d | | Open issues (now) | 605 | 4 | | Stars delta | +855 (30d) | +63 (30d) | | Open issues delta | -80 (30d) | +1 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/microsoft-agent-framework/trust.md) | [trust report](/tools/pguso-agents-from-scratch/trust.md) | ## Shared compatibility - **Python**: [agent-framework](/tools/microsoft-agent-framework.md) - Python runtime; [agents-from-scratch](/tools/pguso-agents-from-scratch.md) - Python runtime ## 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: agents-from-scratch - **Requirements:** Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs. - **Adopt for:** agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. - **License detail:** MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. ## Choose when ### Choose agent-framework if… - 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 agents-from-scratch if… - Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.. - Tags unique to agents-from-scratch: agent-architecture, ai-agents, llm, local-llm. - You plan to teach yourself or others about the fundamentals of creating AI agents from ground zero with complete transparency into each layer of architecture. ## 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 agents-from-scratch - You are working on an application that needs to be deployed quickly. The tool's approach from first principles can be time-consuming compared to using established frameworks. - If you need scalability or cloud capabilities such as easy scaling with demand, this tool will not provide these features since it strictly operates on local infrastructure. ## Common questions ### What is the difference between agent-framework and agents-from-scratch? agent-framework: Framework for building and deploying AI agents and multi-agent workflows. agents-from-scratch: Build AI agents locally without relying on frameworks or cloud APIs.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-framework over agents-from-scratch? Choose agent-framework over agents-from-scratch when 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 agents-from-scratch over agent-framework? Choose agents-from-scratch over agent-framework when Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.; Tags unique to agents-from-scratch: agent-architecture, ai-agents, llm, local-llm; You plan to teach yourself or others about the fundamentals of creating AI agents from ground zero with complete transparency into each layer of architecture. ### 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 agents-from-scratch? You are working on an application that needs to be deployed quickly. The tool's approach from first principles can be time-consuming compared to using established frameworks. If you need scalability or cloud capabilities such as easy scaling with demand, this tool will not provide these features since it strictly operates on local infrastructure. ### Is agent-framework or agents-from-scratch more popular on GitHub? agent-framework has more GitHub stars (13,573 vs 1,017). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-framework and agents-from-scratch open source? Yes - both are open-source projects on GitHub (agent-framework: MIT, agents-from-scratch: MIT). ### Where can I find alternatives to agent-framework or agents-from-scratch? GraphCanon lists graph-backed alternatives at [agent-framework alternatives](/tools/microsoft-agent-framework/alternatives) and [agents-from-scratch alternatives](/tools/pguso-agents-from-scratch/alternatives) ([agent-framework markdown twin](/tools/microsoft-agent-framework/alternatives.md), [agents-from-scratch markdown twin](/tools/pguso-agents-from-scratch/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-pguso-agents-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-framework or agents-from-scratch? agent-framework: Very active. agents-from-scratch: Steady. 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 agents-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-framework trust report](/tools/microsoft-agent-framework/trust); [agents-from-scratch trust report](/tools/pguso-agents-from-scratch/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/_