--- title: "leva vs auto-evaluator" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/kieranklaassen-leva-vs-langchain-ai-auto-evaluator" tools: ["kieranklaassen-leva", "langchain-ai-auto-evaluator"] --- # leva vs auto-evaluator *GraphCanon updated Aug 8, 2026* ## Verdict Pick leva when leva is primarily Ruby; auto-evaluator is TypeScript; pick auto-evaluator when auto-evaluator is primarily TypeScript; leva is Ruby. [leva](https://github.com/kieranklaassen/leva) reports 142 GitHub stars, 7 forks, and 4 open issues, last pushed Jun 3, 2026. [auto-evaluator](https://autoevaluator.langchain.com/) has 783 stars, 102 forks, and 21 open issues, last pushed Jun 26, 2025. Figures are from public GitHub metadata via [leva's repository](https://github.com/kieranklaassen/leva) and [auto-evaluator's repository](https://github.com/langchain-ai/auto-evaluator). | | [leva](/tools/kieranklaassen-leva.md) | [auto-evaluator](/tools/langchain-ai-auto-evaluator.md) | | --- | --- | --- | | Tagline | LLM Evaluation Framework for Rails apps | auto-evaluator | | Stars | 142 | 783 | | Forks | 7 | 102 | | Open issues | 4 | 21 | | Language | Ruby | TypeScript | | Adopt for | Leva is an LLM evaluation framework for Ruby on Rails apps, aiming to use production data directly in the evaluation process. | - | | Persona | - | - | | Runtime | - | - | | License | MIT | Other | | Categories | Evaluation & Observability | Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [leva](/tools/kieranklaassen-leva.md) | [auto-evaluator](/tools/langchain-ai-auto-evaluator.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Archived (8%) | | Days since push | 55d | 408d | | Archived on GitHub | No | Yes | | Open issues (now) | 4 | 21 | | Owner type | User | Organization | | Full report | [trust report](/tools/kieranklaassen-leva/trust.md) | [trust report](/tools/langchain-ai-auto-evaluator/trust.md) | ## Decision facts: leva - **Adopt for:** Leva is an LLM evaluation framework for Ruby on Rails apps, aiming to use production data directly in the evaluation process. ## Choose when ### Choose leva if… - leva is primarily Ruby; auto-evaluator is TypeScript. - License: leva is MIT, auto-evaluator is Other. - Tags unique to leva: llm, llm-evaluation, rails-apps, ruby-on-rails. - You are working with Ruby on Rails applications and need a tool specific to this environment ### Choose auto-evaluator if… - auto-evaluator is primarily TypeScript; leva is Ruby. - License: auto-evaluator is Other, leva is MIT. - Tags unique to auto-evaluator: auto-evaluation, railway, typescript, vercel. - Use auto-evaluator when you are working with TypeScript and need an integrated solution for evaluating AI models ## When NOT to use leva - If your application is not built using Ruby on Rails, Leva may not be the best fit - For scenarios requiring broader cross-platform support or with non-Rails production data integration needs, consider other tools ## When NOT to use auto-evaluator - Avoid using auto-evaluator if you require a multi-language support environment, as it focuses solely on TypeScript - Do not use this tool if your project's hosting requirements do not align with using Vercel or Railway ## Common questions ### What is the difference between leva and auto-evaluator? leva: LLM Evaluation Framework for Rails apps. auto-evaluator: auto-evaluator. See the comparison table for live GitHub stats and shared categories. ### When should I choose leva over auto-evaluator? Choose leva over auto-evaluator when leva is primarily Ruby; auto-evaluator is TypeScript; License: leva is MIT, auto-evaluator is Other; Tags unique to leva: llm, llm-evaluation, rails-apps, ruby-on-rails; You are working with Ruby on Rails applications and need a tool specific to this environment. ### When should I choose auto-evaluator over leva? Choose auto-evaluator over leva when auto-evaluator is primarily TypeScript; leva is Ruby; License: auto-evaluator is Other, leva is MIT; Tags unique to auto-evaluator: auto-evaluation, railway, typescript, vercel; Use auto-evaluator when you are working with TypeScript and need an integrated solution for evaluating AI models. ### When should I avoid leva? If your application is not built using Ruby on Rails, Leva may not be the best fit For scenarios requiring broader cross-platform support or with non-Rails production data integration needs, consider other tools ### When should I avoid auto-evaluator? Avoid using auto-evaluator if you require a multi-language support environment, as it focuses solely on TypeScript Do not use this tool if your project's hosting requirements do not align with using Vercel or Railway ### Is leva or auto-evaluator more popular on GitHub? auto-evaluator has more GitHub stars (783 vs 142). Stars measure visibility, not whether either tool fits your constraints. ### Are leva and auto-evaluator open source? Yes - both are open-source projects on GitHub (leva: MIT, auto-evaluator: Other). ### Where can I find alternatives to leva or auto-evaluator? GraphCanon lists graph-backed alternatives at [leva alternatives](/tools/kieranklaassen-leva/alternatives) and [auto-evaluator alternatives](/tools/langchain-ai-auto-evaluator/alternatives) ([leva markdown twin](/tools/kieranklaassen-leva/alternatives.md), [auto-evaluator markdown twin](/tools/langchain-ai-auto-evaluator/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/kieranklaassen-leva-vs-langchain-ai-auto-evaluator.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, leva or auto-evaluator? leva: Steady. auto-evaluator: Archived. 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 leva and auto-evaluator? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [leva trust report](/tools/kieranklaassen-leva/trust); [auto-evaluator trust report](/tools/langchain-ai-auto-evaluator/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=kieranklaassen-leva`](/api/graphcanon/graph?tool=kieranklaassen-leva) - 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/_