--- title: "RD-Agent vs agency" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-rd-agent-vs-neurocult-agency" tools: ["microsoft-rd-agent", "neurocult-agency"] --- # RD-Agent vs agency *GraphCanon updated Aug 21, 2026* ## Verdict Pick RD-Agent if rD-Agent is an automation tool for AI-driven R&D processes, focusing on data and model development using Python with support from Docker installations; pick agency if agency is a Go-idiomatic library aimed at developers looking to work with Large Language Models and generative AI techniques. [RD-Agent](https://rdagent.azurewebsites.net/) reports 14k GitHub stars, 1.8k forks, and 198 open issues, last pushed Aug 4, 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 [RD-Agent's repository](https://github.com/microsoft/RD-Agent) and [agency's repository](https://github.com/neurocult/agency). | | [RD-Agent](/tools/microsoft-rd-agent.md) | [agency](/tools/neurocult-agency.md) | | --- | --- | --- | | Tagline | Automating high-value R&D processes through AI-driven data science and model development. | Library for exploring Large Language Models and generative AI in Go | | Stars | 14,275 | 514 | | Forks | 1,834 | 36 | | Open issues | 198 | 4 | | Language | Python | Go | | Adopt for | RD-Agent is an automation tool for AI-driven R&D processes, focusing on data and model development using Python with support from Docker installations. | Agency is a Go-idiomatic library aimed at developers looking to work with Large Language Models and generative AI techniques. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | AI Agents, Data & Retrieval, Model Training | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [RD-Agent](/tools/microsoft-rd-agent.md) | [agency](/tools/neurocult-agency.md) | | --- | --- | --- | | Maintenance | Active (82%) | Dormant (18%) | | Days since push | 14d | 589d | | Open issues (now) | 198 | 4 | | Stars delta | +332 (30d) | +2 (30d) | | Open issues delta | +5 (30d) | 0 (30d) | | Full report | [trust report](/tools/microsoft-rd-agent/trust.md) | [trust report](/tools/neurocult-agency/trust.md) | ## Decision facts: RD-Agent - **Pricing:** freemium - RD-Agent operates under the MIT license allowing free use of the tool. Its framework for R&D automation can be expanded with premium services for enterprise-level support and integration if needed. - **Requirements:** Requires Docker; Ensure Docker is installed beforehand and accessible without `sudo` by the current user for RD-Agent operation.; Supports Python installations via PyPI or development setup from source, which also requires installation of dependencies as per the documentation. - **Adopt for:** RD-Agent is an automation tool for AI-driven R&D processes, focusing on data and model development using Python with support from Docker installations. ## 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 RD-Agent if… - RD-Agent is primarily Python; agency is Go. - Pricing: RD-Agent operates under the MIT license allowing free use of the tool. Its framework for R&D automation can be expanded with premium services for enterprise-level support and integration if needed.. - Requirements: Requires Docker; Ensure Docker is installed beforehand and accessible without `sudo` by the current user for RD-Agent operation.; Supports Python installations via PyPI or development setup from source, which also requires installation of dependencies as per the documentation.. - Tags unique to RD-Agent: agent, ai, automation, data-mining. - Also covers Data & Retrieval, Model Training. - When you require automation in high-value R&D tasks that revolve around data science and model development within the AI domain. ### Choose agency if… - agency is primarily Go; RD-Agent is Python. - 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 RD-Agent - When the need arises to work in an environment where Python cannot be used or there is a requirement for another programming language framework that complements existing infrastructure better. - If your development team lacks expertise with Docker and is not willing or able to adopt it, as most scenarios within RD-Agent require a solid Docker setup. ## 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 RD-Agent and agency? RD-Agent: Automating high-value R&D processes through AI-driven data science and model development.. 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 RD-Agent over agency? Choose RD-Agent over agency when RD-Agent is primarily Python; agency is Go; Pricing: RD-Agent operates under the MIT license allowing free use of the tool. Its framework for R&D automation can be expanded with premium services for enterprise-level support and integration if needed.; Requirements: Requires Docker; Ensure Docker is installed beforehand and accessible without `sudo` by the current user for RD-Agent operation.; Supports Python installations via PyPI or development setup from source, which also requires installation of dependencies as per the documentation.; Tags unique to RD-Agent: agent, ai, automation, data-mining; Also covers Data & Retrieval, Model Training; When you require automation in high-value R&D tasks that revolve around data science and model development within the AI domain. ### When should I choose agency over RD-Agent? Choose agency over RD-Agent when agency is primarily Go; RD-Agent is Python; 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 RD-Agent? When the need arises to work in an environment where Python cannot be used or there is a requirement for another programming language framework that complements existing infrastructure better. If your development team lacks expertise with Docker and is not willing or able to adopt it, as most scenarios within RD-Agent require a solid Docker setup. ### 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 RD-Agent or agency more popular on GitHub? RD-Agent has more GitHub stars (14,275 vs 514). Stars measure visibility, not whether either tool fits your constraints. ### Are RD-Agent and agency open source? Yes - both are open-source projects on GitHub (RD-Agent: MIT, agency: MIT). ### Where can I find alternatives to RD-Agent or agency? GraphCanon lists graph-backed alternatives at [RD-Agent alternatives](/tools/microsoft-rd-agent/alternatives) and [agency alternatives](/tools/neurocult-agency/alternatives) ([RD-Agent markdown twin](/tools/microsoft-rd-agent/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/microsoft-rd-agent-vs-neurocult-agency.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, RD-Agent or agency? RD-Agent: 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 RD-Agent and agency? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [RD-Agent trust report](/tools/microsoft-rd-agent/trust); [agency trust report](/tools/neurocult-agency/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-rd-agent`](/api/graphcanon/graph?tool=microsoft-rd-agent) - 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/_