--- title: "apm vs agency" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-apm-vs-operand-agency" tools: ["microsoft-apm", "operand-agency"] --- # apm vs agency *GraphCanon updated Aug 21, 2026* ## Verdict Pick apm if agent Package Manager is specialized for managing AI agent packages and their dependencies using Python under MIT license; pick agency if agency is a fast and minimal Python-based framework for developing agentic systems that excels in its streamlined approach to creating autonomous agents. [apm](https://microsoft.github.io/apm/) reports 3.4k GitHub stars, 301 forks, and 164 open issues, last pushed Jul 25, 2026. [agency](https://createwith.agency) has 489 stars, 28 forks, and 19 open issues, last pushed Jun 10, 2026. Figures are from public GitHub metadata via [apm's repository](https://github.com/microsoft/apm) and [agency's repository](https://github.com/operand/agency). | | [apm](/tools/microsoft-apm.md) | [agency](/tools/operand-agency.md) | | --- | --- | --- | | Tagline | Agent Package Manager | A fast and minimal framework for building agentic systems | | Stars | 3,385 | 489 | | Forks | 301 | 28 | | Open issues | 164 | 19 | | Language | Python | Python | | Adopt for | Agent Package Manager is specialized for managing AI agent packages and their dependencies using Python under MIT license. | Agency is a fast and minimal Python-based framework for developing agentic systems that excels in its streamlined approach to creating autonomous agents. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | AI Agents | AI Agents | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [apm](/tools/microsoft-apm.md) | [agency](/tools/operand-agency.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Steady (60%) | | Days since push | 2d | 71d | | Open issues (now) | 164 | 19 | | Stars delta | Unknown | +2 (30d) | | Open issues delta | Unknown | 0 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/microsoft-apm/trust.md) | [trust report](/tools/operand-agency/trust.md) | ## Decision facts: apm - **Adopt for:** Agent Package Manager is specialized for managing AI agent packages and their dependencies using Python under MIT license. ## Decision facts: agency - **Adopt for:** Agency is a fast and minimal Python-based framework for developing agentic systems that excels in its streamlined approach to creating autonomous agents. ## Choose when ### Choose apm if… - Tags unique to apm: ai-agents, claude-code, codex-cli, context-engineering. - You focus on AI agent development with specific package needs - More GitHub stars (3.4k vs 489) - visibility, not fit. ### Choose agency if… - Tags unique to agency: actor-model, agent-framework, autonomous-agents. - When you prefer a lightweight solution for building autonomous agent systems without the need for extensive configuration or complex dependencies. - Leaner open-issue backlog (19). ## When NOT to use apm - You prefer generic software or non-AI-specific package managers - Requirements include support for languages other than Python ## When NOT to use agency - If your development requires deeply integrated functionalities that would necessitate a heavier, more feature-rich framework. - In scenarios where you need robust tooling for large-scale deployment and management as Agency does not offer extensive LLMOps (LLM Operations) capabilities beyond its minimalistic design. ## Common questions ### What is the difference between apm and agency? apm: Agent Package Manager. 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 apm over agency? Choose apm over agency when Tags unique to apm: ai-agents, claude-code, codex-cli, context-engineering; You focus on AI agent development with specific package needs; More GitHub stars (3.4k vs 489) - visibility, not fit. ### When should I choose agency over apm? Choose agency over apm when Tags unique to agency: actor-model, agent-framework, autonomous-agents; When you prefer a lightweight solution for building autonomous agent systems without the need for extensive configuration or complex dependencies; Leaner open-issue backlog (19). ### When should I avoid apm? You prefer generic software or non-AI-specific package managers Requirements include support for languages other than Python ### When should I avoid agency? If your development requires deeply integrated functionalities that would necessitate a heavier, more feature-rich framework. In scenarios where you need robust tooling for large-scale deployment and management as Agency does not offer extensive LLMOps (LLM Operations) capabilities beyond its minimalistic design. ### Is apm or agency more popular on GitHub? apm has more GitHub stars (3,385 vs 489). Stars measure visibility, not whether either tool fits your constraints. ### Are apm and agency open source? Yes - both are open-source projects on GitHub (apm: MIT, agency: MIT). ### Where can I find alternatives to apm or agency? GraphCanon lists graph-backed alternatives at [apm alternatives](/tools/microsoft-apm/alternatives) and [agency alternatives](/tools/operand-agency/alternatives) ([apm markdown twin](/tools/microsoft-apm/alternatives.md), [agency markdown twin](/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 [this comparison](/compare/microsoft-apm-vs-operand-agency.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, apm or agency? apm: Very active. agency: 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 apm and agency? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [apm trust report](/tools/microsoft-apm/trust); [agency trust report](/tools/operand-agency/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-apm`](/api/graphcanon/graph?tool=microsoft-apm) - 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/_