--- title: "autogen vs agency" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-autogen-vs-operand-agency" tools: ["microsoft-autogen", "operand-agency"] --- # autogen vs agency Neutral, constraint-first comparison with live GitHub stats. | | [autogen](/tools/microsoft-autogen.md) | [agency](/tools/operand-agency.md) | | --- | --- | --- | | Tagline | A framework for creating multi-agent AI applications | A fast and minimal framework for building agentic systems. | | Stars | 59,573 | 487 | | Forks | 8,967 | 28 | | Open issues | 930 | 19 | | Language | Python | Python | | Adopt for | AutoGen is a framework for developing multi-agent AI applications that can act autonomously or alongside humans. It's currently in maintenance mode with no additional features planned and users are encouraged to migrate. | Agency provides an Actor model framework that enables the development of custom agent-based applications with support for concurrency, networked agents through AMQP, and detailed observability features. | | Persona | - | - | | Runtime | - | - | | License | CC-BY-4.0 | MIT | | Categories | AI Agents, LLM Frameworks | AI Agents | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [autogen](/tools/microsoft-autogen.md) | [agency](/tools/operand-agency.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Active (82%) | | Days since push | 83d | 27d | | Open issues (now) | 930 | 19 | | Owner type | Organization | User | | Security scan | No lockfile | 5 low (5 low) | | Full report | [trust report](/tools/microsoft-autogen/trust.md) | [trust report](/tools/operand-agency/trust.md) | **Typed relationship:** autogen _(integrates with)_ agency Agency can integrate with autogen to create sophisticated multi-agent systems, as both frameworks focus on developing flexible agent architectures. ## Shared compatibility - **Python**: [autogen](/tools/microsoft-autogen.md) - Python runtime; [agency](/tools/operand-agency.md) - Python runtime ## Decision facts: autogen - **Requirements:** AutoGen requires Python 3.10 or later. - **Adopt for:** AutoGen is a framework for developing multi-agent AI applications that can act autonomously or alongside humans. It's currently in maintenance mode with no additional features planned and users are encouraged to migrate. ## Decision facts: agency - **Pricing:** freemium - The framework is available under an MIT license, making it free to use. However, advanced services like detailed support or commercial customizations might require a contract with additional costs. - **Requirements:** Min 1 GB RAM; Requires Docker; Docker is used for deployment but not mandatory; the framework can be set up in any environment that supports Python and potentially RabbitMQ for networked use. - **Adopt for:** Agency provides an Actor model framework that enables the development of custom agent-based applications with support for concurrency, networked agents through AMQP, and detailed observability features. ## Choose when ### Choose autogen if… - License: autogen is CC-BY-4.0, agency is MIT. - Requirements: AutoGen requires Python 3.10 or later.. - Agency can integrate with autogen to create sophisticated multi-agent systems, as both frameworks focus on developing flexible agent architectures. - Tags unique to autogen: autogen, agentic. - Also covers LLM Frameworks. - You should use AutoGen if you have an existing project built on it and desire to maintain its current functionality without introducing advanced enterprise features or extensive new capabilities. ### Choose agency if… - License: agency is MIT, autogen is CC-BY-4.0. - Pricing: The framework is available under an MIT license, making it free to use. However, advanced services like detailed support or commercial customizations might require a contract with additional costs.. - Requirements: Min 1 GB RAM; Requires Docker; Docker is used for deployment but not mandatory; the framework can be set up in any environment that supports Python and potentially RabbitMQ for networked use.. - Agency can integrate with autogen to create sophisticated multi-agent systems, as both frameworks focus on developing flexible agent architectures. - Tags unique to agency: llmops, machine-learning, actor-model, agi. - - You need to develop a system where agents can be integrated in a concurrent or distributed environment using Python. ## When NOT to use autogen - Do not use AutoGen if you are planning to build a production-ready application that requires long-term support, enterprise-grade orchestration features, or multi-provider model support. - Avoid using this tool if your project needs future-proof development with new and continuous enhancements as the framework is in maintenance mode. ## When NOT to use agency - - If your primary requirement is to implement generic AI functionalities without focusing on agent interaction and custom architectures, preferring simplicity over flexibility. - - For systems requiring extremely high performance for processing large datasets where overhead from the agentic model might introduce unacceptable latency. ## Common questions ### What is the difference between autogen and agency? autogen: A framework for creating multi-agent AI applications. agency: A fast and minimal framework for building agentic systems.. See the comparison table for live GitHub stats and shared categories. ### When should I choose autogen over agency? Choose autogen over agency when License: autogen is CC-BY-4.0, agency is MIT; Requirements: AutoGen requires Python 3.10 or later.; Agency can integrate with autogen to create sophisticated multi-agent systems, as both frameworks focus on developing flexible agent architectures; Tags unique to autogen: autogen, agentic; Also covers LLM Frameworks; You should use AutoGen if you have an existing project built on it and desire to maintain its current functionality without introducing advanced enterprise features or extensive new capabilities. ### When should I choose agency over autogen? Choose agency over autogen when License: agency is MIT, autogen is CC-BY-4.0; Pricing: The framework is available under an MIT license, making it free to use. However, advanced services like detailed support or commercial customizations might require a contract with additional costs.; Requirements: Min 1 GB RAM; Requires Docker; Docker is used for deployment but not mandatory; the framework can be set up in any environment that supports Python and potentially RabbitMQ for networked use.; Agency can integrate with autogen to create sophisticated multi-agent systems, as both frameworks focus on developing flexible agent architectures; Tags unique to agency: llmops, machine-learning, actor-model, agi; - You need to develop a system where agents can be integrated in a concurrent or distributed environment using Python. ### When should I avoid autogen? Do not use AutoGen if you are planning to build a production-ready application that requires long-term support, enterprise-grade orchestration features, or multi-provider model support. Avoid using this tool if your project needs future-proof development with new and continuous enhancements as the framework is in maintenance mode. ### When should I avoid agency? - If your primary requirement is to implement generic AI functionalities without focusing on agent interaction and custom architectures, preferring simplicity over flexibility. - For systems requiring extremely high performance for processing large datasets where overhead from the agentic model might introduce unacceptable latency. ### Is autogen or agency more popular on GitHub? autogen has more GitHub stars (59,573 vs 487). Stars measure visibility, not whether either tool fits your constraints. ### Are autogen and agency open source? Yes - both are open-source projects on GitHub (autogen: CC-BY-4.0, agency: MIT). ### Where can I find alternatives to autogen or agency? GraphCanon lists graph-backed alternatives at /tools/microsoft-autogen/alternatives and /tools/operand-agency/alternatives (/tools/microsoft-autogen/alternatives.md, /tools/operand-agency/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 /compare/microsoft-autogen-vs-operand-agency.md mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, autogen or agency? autogen: Steady. agency: 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 autogen and agency? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: autogen: /tools/microsoft-autogen/trust; agency: /tools/operand-agency/trust. --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-autogen`](/api/graphcanon/graph?tool=microsoft-autogen) - 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/_