--- title: "llm_agents vs agency" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/mpaepper-llm-agents-vs-operand-agency" tools: ["mpaepper-llm-agents", "operand-agency"] --- # llm_agents vs agency *GraphCanon updated Aug 21, 2026* ## Verdict Pick llm_agents if llm_agents is a Python library enabling users to build simple agents directed by large language models, featuring functions like executing Python code and using Google search; 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. [llm_agents](https://www.paepper.com/blog/posts/intelligent-agents-guided-by-llms/) reports 1.1k GitHub stars, 85 forks, and 3 open issues, last pushed Jun 23, 2025. [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 [llm_agents's repository](https://github.com/mpaepper/llm_agents) and [agency's repository](https://github.com/operand/agency). | | [llm_agents](/tools/mpaepper-llm-agents.md) | [agency](/tools/operand-agency.md) | | --- | --- | --- | | Tagline | Library to build agents controlled by LLMs | A fast and minimal framework for building agentic systems | | Stars | 1,053 | 489 | | Forks | 85 | 28 | | Open issues | 3 | 19 | | Language | Python | Python | | Adopt for | llm_agents is a Python library enabling users to build simple agents directed by large language models, featuring functions like executing Python code and using Google search. | 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._ | | [llm_agents](/tools/mpaepper-llm-agents.md) | [agency](/tools/operand-agency.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Steady (60%) | | Days since push | 418d | 71d | | Open issues (now) | 3 | 19 | | Stars delta | +3 (30d) | +2 (30d) | | Full report | [trust report](/tools/mpaepper-llm-agents/trust.md) | [trust report](/tools/operand-agency/trust.md) | ## Shared compatibility - **Python**: [llm_agents](/tools/mpaepper-llm-agents.md) - Python runtime; [agency](/tools/operand-agency.md) - Python runtime ## Decision facts: llm_agents - **Requirements:** Min 1 GB RAM; Requires the installation of requirements specified by running `pip install -r requirements.txt` followed by `pip install -e .`.; Dependencies include setting up environment variables for `OPENAI_API_KEY` to use OpenAI API and optionally `SERPAPI_API_KEY` if Google search tool is utilized. - **Adopt for:** llm_agents is a Python library enabling users to build simple agents directed by large language models, featuring functions like executing Python code and using Google search. ## 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 llm_agents if… - Requirements: Min 1 GB RAM; Requires the installation of requirements specified by running `pip install -r requirements.txt` followed by `pip install -e .`.; Dependencies include setting up environment variables for `OPENAI_API_KEY` to use OpenAI API and optionally `SERPAPI_API_KEY` if Google search tool is utilized.. - Tags unique to llm_agents: deep-learning, langchain, llms, machine-learning. - Use llm_agents when you require a lightweight solution for building agents controlled by LLMs with specific tools such as Python REPL execution or Hacker News search. ### 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. - More recently updated (last pushed Jun 10, 2026). ## When NOT to use llm_agents - Avoid llm_agents if you need a more robust and feature-rich product for complex tasks that require extensive integration capabilities beyond Python REPL, Google search, and Hacker News. - Do not choose it when you are looking for advanced abstraction layers like those found in LangChain, as llm_agents aims to remain simple with fewer files and a straightforward core. ## 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 llm_agents and agency? llm_agents: Library to build agents controlled by LLMs. 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 llm_agents over agency? Choose llm_agents over agency when Requirements: Min 1 GB RAM; Requires the installation of requirements specified by running `pip install -r requirements.txt` followed by `pip install -e .`.; Dependencies include setting up environment variables for `OPENAI_API_KEY` to use OpenAI API and optionally `SERPAPI_API_KEY` if Google search tool is utilized.; Tags unique to llm_agents: deep-learning, langchain, llms, machine-learning; Use llm_agents when you require a lightweight solution for building agents controlled by LLMs with specific tools such as Python REPL execution or Hacker News search. ### When should I choose agency over llm_agents? Choose agency over llm_agents 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; More recently updated (last pushed Jun 10, 2026). ### When should I avoid llm_agents? Avoid llm_agents if you need a more robust and feature-rich product for complex tasks that require extensive integration capabilities beyond Python REPL, Google search, and Hacker News. Do not choose it when you are looking for advanced abstraction layers like those found in LangChain, as llm_agents aims to remain simple with fewer files and a straightforward core. ### 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 llm_agents or agency more popular on GitHub? llm_agents has more GitHub stars (1,053 vs 489). Stars measure visibility, not whether either tool fits your constraints. ### Are llm_agents and agency open source? Yes - both are open-source projects on GitHub (llm_agents: MIT, agency: MIT). ### Where can I find alternatives to llm_agents or agency? GraphCanon lists graph-backed alternatives at [llm_agents alternatives](/tools/mpaepper-llm-agents/alternatives) and [agency alternatives](/tools/operand-agency/alternatives) ([llm_agents markdown twin](/tools/mpaepper-llm-agents/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/mpaepper-llm-agents-vs-operand-agency.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, llm_agents or agency? llm_agents: Dormant. 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 llm_agents and agency? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [llm_agents trust report](/tools/mpaepper-llm-agents/trust); [agency trust report](/tools/operand-agency/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=mpaepper-llm-agents`](/api/graphcanon/graph?tool=mpaepper-llm-agents) - 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/_