--- title: "leva vs autogen" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/kieranklaassen-leva-vs-microsoft-autogen" tools: ["kieranklaassen-leva", "microsoft-autogen"] --- # leva vs autogen *GraphCanon updated Jul 11, 2026* ## Verdict Pick leva when leva is primarily Ruby; autogen is Python; pick autogen when autogen is primarily Python; leva is Ruby. [leva](https://github.com/kieranklaassen/leva) reports 141 GitHub stars, 7 forks, and 4 open issues, last pushed Jun 3, 2026. [autogen](https://microsoft.github.io/autogen/) has 60k stars, 9.0k forks, and 945 open issues, last pushed Apr 15, 2026. Figures are from public GitHub metadata via [leva's repository](https://github.com/kieranklaassen/leva) and [autogen's repository](https://github.com/microsoft/autogen). | | [leva](/tools/kieranklaassen-leva.md) | [autogen](/tools/microsoft-autogen.md) | | --- | --- | --- | | Tagline | LLM Evaluation Framework for Rails apps to be used with production data. | A programming framework for agentic AI | | Stars | 141 | 59,658 | | Forks | 7 | 8,983 | | Open issues | 4 | 945 | | Language | Ruby | Python | | Adopt for | - | AutoGen is a Python-based framework for developing and managing agentic AI systems. It includes the AutoGen Studio for no-code GUI setup, integrating with various models. | | Persona | - | - | | Runtime | - | - | | License | MIT | CC-BY-4.0 | | Categories | Evaluation & Observability, LLM Frameworks | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [leva](/tools/kieranklaassen-leva.md) | [autogen](/tools/microsoft-autogen.md) | | --- | --- | --- | | Days since push | 37d | 87d | | Open issues (now) | 4 | 945 | | Owner type | User | Organization | | Full report | [trust report](/tools/kieranklaassen-leva/trust.md) | [trust report](/tools/microsoft-autogen/trust.md) | ## Decision facts: autogen - **Requirements:** Min 4 GB RAM; AutoGen requires Python 3.10 or later.; Ensure security when connecting to MCP servers due to the potential for local command execution and sensitive information exposure. - **Adopt for:** AutoGen is a Python-based framework for developing and managing agentic AI systems. It includes the AutoGen Studio for no-code GUI setup, integrating with various models. ## Choose when ### Choose leva if… - leva is primarily Ruby; autogen is Python. - License: leva is MIT, autogen is CC-BY-4.0. - Tags unique to leva: llm, llm-evaluation, ruby, ruby-on-rails. - Also covers Evaluation & Observability. ### Choose autogen if… - autogen is primarily Python; leva is Ruby. - License: autogen is CC-BY-4.0, leva is MIT. - Requirements: Min 4 GB RAM; AutoGen requires Python 3.10 or later.; Ensure security when connecting to MCP servers due to the potential for local command execution and sensitive information exposure.. - Tags unique to autogen: agentic-agi, agents, ai, autogen. - Also covers AI Agents. - You need a framework that supports integration with multiple AI models via OpenAI's chat completion client. ## When NOT to use leva - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ## When NOT to use autogen - If you require tools supporting multiple programming languages beyond Python, as AutoGen is strictly a Python-based framework. - When deploying in environments where connecting to external servers (like those used by MCP) could pose security risks or is prohibited. - You need solutions which do not involve additional installations for server components such as `playwright/mcp`, as AutoGen requires this setup for certain functionalities. ## Common questions ### What is the difference between leva and autogen? leva: LLM Evaluation Framework for Rails apps to be used with production data.. autogen: A programming framework for agentic AI. See the comparison table for live GitHub stats and shared categories. ### When should I choose leva over autogen? Choose leva over autogen when leva is primarily Ruby; autogen is Python; License: leva is MIT, autogen is CC-BY-4.0; Tags unique to leva: llm, llm-evaluation, ruby, ruby-on-rails; Also covers Evaluation & Observability. ### When should I choose autogen over leva? Choose autogen over leva when autogen is primarily Python; leva is Ruby; License: autogen is CC-BY-4.0, leva is MIT; Requirements: Min 4 GB RAM; AutoGen requires Python 3.10 or later.; Ensure security when connecting to MCP servers due to the potential for local command execution and sensitive information exposure.; Tags unique to autogen: agentic-agi, agents, ai, autogen; Also covers AI Agents; You need a framework that supports integration with multiple AI models via OpenAI's chat completion client. ### When should I avoid leva? Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ### When should I avoid autogen? If you require tools supporting multiple programming languages beyond Python, as AutoGen is strictly a Python-based framework. When deploying in environments where connecting to external servers (like those used by MCP) could pose security risks or is prohibited. You need solutions which do not involve additional installations for server components such as `playwright/mcp`, as AutoGen requires this setup for certain functionalities. ### Is leva or autogen more popular on GitHub? autogen has more GitHub stars (59,658 vs 141). Stars measure visibility, not whether either tool fits your constraints. ### Are leva and autogen open source? Yes - both are open-source projects on GitHub (leva: MIT, autogen: CC-BY-4.0). ### Where can I find alternatives to leva or autogen? GraphCanon lists graph-backed alternatives at [leva alternatives](/tools/kieranklaassen-leva/alternatives) and [autogen alternatives](/tools/microsoft-autogen/alternatives) ([leva markdown twin](/tools/kieranklaassen-leva/alternatives.md), [autogen markdown twin](/tools/microsoft-autogen/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-microsoft-autogen.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, leva or autogen? leva: Steady. autogen: 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 leva and autogen? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [leva trust report](/tools/kieranklaassen-leva/trust); [autogen trust report](/tools/microsoft-autogen/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/_