--- title: "adk-python vs agency" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/google-adk-python-vs-neurocult-agency" tools: ["google-adk-python", "neurocult-agency"] --- # adk-python vs agency *GraphCanon updated Aug 21, 2026* ## Verdict Pick adk-python if adk-python provides tools for developing sophisticated AI agents with a focus on flexibility and control, particularly suited for multi-agent systems; pick agency if agency is a Go-idiomatic library aimed at developers looking to work with Large Language Models and generative AI techniques. [adk-python](https://google.github.io/adk-docs/) reports 21k GitHub stars, 3.9k forks, and 566 open issues, last pushed Aug 18, 2026. [agency](https://github.com/neurocult/agency) has 514 stars, 36 forks, and 4 open issues, last pushed Jan 8, 2025. Figures are from public GitHub metadata via [adk-python's repository](https://github.com/google/adk-python) and [agency's repository](https://github.com/neurocult/agency). | | [adk-python](/tools/google-adk-python.md) | [agency](/tools/neurocult-agency.md) | | --- | --- | --- | | Tagline | A Python toolkit for building, evaluating, and deploying AI agents | Library for exploring Large Language Models and generative AI in Go | | Stars | 21,180 | 514 | | Forks | 3,860 | 36 | | Open issues | 566 | 4 | | Language | Python | Go | | Adopt for | adk-python provides tools for developing sophisticated AI agents with a focus on flexibility and control, particularly suited for multi-agent systems. | Agency is a Go-idiomatic library aimed at developers looking to work with Large Language Models and generative AI techniques. | | Persona | - | - | | Runtime | - | - | | License | adk-python is available under the Apache-2.0 license, allowing both commercial and non-commercial use with appropriate attribution. | MIT | | Categories | AI Agents | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [adk-python](/tools/google-adk-python.md) | [agency](/tools/neurocult-agency.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Dormant (18%) | | Days since push | 0d | 589d | | Open issues (now) | 566 | 4 | | Stars delta | +522 (30d) | +2 (30d) | | Open issues delta | -76 (30d) | 0 (30d) | | Full report | [trust report](/tools/google-adk-python/trust.md) | [trust report](/tools/neurocult-agency/trust.md) | ## Decision facts: adk-python - **Requirements:** Requires Python 3.10+ for installation. - **Adopt for:** adk-python provides tools for developing sophisticated AI agents with a focus on flexibility and control, particularly suited for multi-agent systems. - **License detail:** adk-python is available under the Apache-2.0 license, allowing both commercial and non-commercial use with appropriate attribution. ## Decision facts: agency - **Pricing:** freemium - Agency is available under MIT license and is free for use, modification, and distribution. Additional services or integrations might involve costs not outlined within the repository. - **Adopt for:** Agency is a Go-idiomatic library aimed at developers looking to work with Large Language Models and generative AI techniques. ## Choose when ### Choose adk-python if… - adk-python is primarily Python; agency is Go. - License: adk-python is Apache-2.0, agency is MIT. - Requirements: Requires Python 3.10+ for installation.. - Tags unique to adk-python: agent, agentic, ai-agents, multi-agent-systems. - You are working on multi-agent systems where multiple AI agents need to collaborate or interact effectively. adk-python offers specific support for defining and orchestrating multi-agent workflows. ### Choose agency if… - agency is primarily Go; adk-python is Python. - License: agency is MIT, adk-python is Apache-2.0. - Pricing: Agency is available under MIT license and is free for use, modification, and distribution. Additional services or integrations might involve costs not outlined within the repository.. - Tags unique to agency: agents, generative-ai, go, language-models. - Also covers LLM Frameworks. - If you're proficient in Go and want to implement LLMs within a familiar ecosystem, consider agency. ## When NOT to use adk-python - If your project does not involve multi-agent interactions or complex orchestration of multiple agents, other frameworks might offer more streamlined solutions. - You prefer using out-of-the-box solutions with less coding complexity. adk-python's code-first approach is best suited for developers looking to deeply customize agent behavior and interactions. ## When NOT to use agency - Avoid agency if your primary programming expertise lies outside of the Go ecosystem. - Not recommended if you require real-time performance characteristics that surpass what typical LLM exploration libraries can provide. ## Common questions ### What is the difference between adk-python and agency? adk-python: A Python toolkit for building, evaluating, and deploying AI agents. agency: Library for exploring Large Language Models and generative AI in Go. See the comparison table for live GitHub stats and shared categories. ### When should I choose adk-python over agency? Choose adk-python over agency when adk-python is primarily Python; agency is Go; License: adk-python is Apache-2.0, agency is MIT; Requirements: Requires Python 3.10+ for installation.; Tags unique to adk-python: agent, agentic, ai-agents, multi-agent-systems; You are working on multi-agent systems where multiple AI agents need to collaborate or interact effectively. adk-python offers specific support for defining and orchestrating multi-agent workflows. ### When should I choose agency over adk-python? Choose agency over adk-python when agency is primarily Go; adk-python is Python; License: agency is MIT, adk-python is Apache-2.0; Pricing: Agency is available under MIT license and is free for use, modification, and distribution. Additional services or integrations might involve costs not outlined within the repository.; Tags unique to agency: agents, generative-ai, go, language-models; Also covers LLM Frameworks; If you're proficient in Go and want to implement LLMs within a familiar ecosystem, consider agency. ### When should I avoid adk-python? If your project does not involve multi-agent interactions or complex orchestration of multiple agents, other frameworks might offer more streamlined solutions. You prefer using out-of-the-box solutions with less coding complexity. adk-python's code-first approach is best suited for developers looking to deeply customize agent behavior and interactions. ### When should I avoid agency? Avoid agency if your primary programming expertise lies outside of the Go ecosystem. Not recommended if you require real-time performance characteristics that surpass what typical LLM exploration libraries can provide. ### Is adk-python or agency more popular on GitHub? adk-python has more GitHub stars (21,180 vs 514). Stars measure visibility, not whether either tool fits your constraints. ### Are adk-python and agency open source? Yes - both are open-source projects on GitHub (adk-python: Apache-2.0, agency: MIT). ### Where can I find alternatives to adk-python or agency? GraphCanon lists graph-backed alternatives at [adk-python alternatives](/tools/google-adk-python/alternatives) and [agency alternatives](/tools/neurocult-agency/alternatives) ([adk-python markdown twin](/tools/google-adk-python/alternatives.md), [agency markdown twin](/tools/neurocult-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/google-adk-python-vs-neurocult-agency.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, adk-python or agency? adk-python: Very active. agency: Dormant. 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 adk-python and agency? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [adk-python trust report](/tools/google-adk-python/trust); [agency trust report](/tools/neurocult-agency/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=google-adk-python`](/api/graphcanon/graph?tool=google-adk-python) - 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/_