--- title: "agentdojo vs judgeval" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/ethz-spylab-agentdojo-vs-judgmentlabs-judgeval" tools: ["ethz-spylab-agentdojo", "judgmentlabs-judgeval"] --- # agentdojo vs judgeval *GraphCanon updated Aug 5, 2026* ## Verdict Pick agentdojo if agentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents; pick judgeval if judgeval is a Python tool that aids in the continuous improvement of AI agents through comprehensive environment data and evaluations, supporting methodologies like reinforcement learning and prompt engineering. [agentdojo](https://agentdojo.spylab.ai/) reports 716 GitHub stars, 188 forks, and 41 open issues, last pushed Jun 2, 2026. [judgeval](https://judgmentlabs.ai/) has 1.0k stars, 95 forks, and 28 open issues, last pushed Jul 27, 2026. Figures are from public GitHub metadata via [agentdojo's repository](https://github.com/ethz-spylab/agentdojo) and [judgeval's repository](https://github.com/JudgmentLabs/judgeval). | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [judgeval](/tools/judgmentlabs-judgeval.md) | | --- | --- | --- | | Tagline | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | The Continuous-Improvement Stack for Agents | | Stars | 716 | 1,047 | | Forks | 188 | 95 | | Open issues | 41 | 28 | | Language | Python | Python | | Adopt for | AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. | Judgeval is a Python tool that aids in the continuous improvement of AI agents through comprehensive environment data and evaluations, supporting methodologies like reinforcement learning and prompt engineering. | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | AI Agents, Evaluation & Observability | AI Agents, Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [judgeval](/tools/judgmentlabs-judgeval.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 63d | 1d | | Open issues (now) | 41 | 28 | | Full report | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | [trust report](/tools/judgmentlabs-judgeval/trust.md) | ## Shared compatibility - **Python**: [agentdojo](/tools/ethz-spylab-agentdojo.md) - Python runtime; [judgeval](/tools/judgmentlabs-judgeval.md) - Python runtime ## Decision facts: agentdojo - **Pricing:** freemium - Open-source under the MIT License. Some advanced features might require additional libraries or APIs. - **Requirements:** Min 8 GB RAM - **Adopt for:** AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. ## Decision facts: judgeval - **Adopt for:** Judgeval is a Python tool that aids in the continuous improvement of AI agents through comprehensive environment data and evaluations, supporting methodologies like reinforcement learning and prompt engineering. ## Choose when ### Choose agentdojo if… - License: agentdojo is MIT, judgeval is Apache-2.0. - Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs.. - Requirements: Min 8 GB RAM. - Tags unique to agentdojo: benchmark, large language models, prompt-injection, security. - AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. ### Choose judgeval if… - License: judgeval is Apache-2.0, agentdojo is MIT. - Tags unique to judgeval: agent, agentic-ai, agents, grpo. - You are working on an AI project where continuous monitoring and enhancement of your agent's performance are critical. ## When NOT to use agentdojo - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. ## When NOT to use judgeval - If you are looking for a tool focused solely on the theoretical aspects of AI development without practical, continuous improvement methodologies. - You require a solution that only supports evaluation metrics and does not offer integrated environment data support, diverging from Judgeval’s comprehensive approach. ## Common questions ### What is the difference between agentdojo and judgeval? agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. judgeval: The Continuous-Improvement Stack for Agents. See the comparison table for live GitHub stats and shared categories. ### When should I choose agentdojo over judgeval? Choose agentdojo over judgeval when License: agentdojo is MIT, judgeval is Apache-2.0; Pricing: Open-source under the MIT License. Some advanced features might require additional libraries or APIs.; Requirements: Min 8 GB RAM; Tags unique to agentdojo: benchmark, large language models, prompt-injection, security; AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. ### When should I choose judgeval over agentdojo? Choose judgeval over agentdojo when License: judgeval is Apache-2.0, agentdojo is MIT; Tags unique to judgeval: agent, agentic-ai, agents, grpo; You are working on an AI project where continuous monitoring and enhancement of your agent's performance are critical. ### When should I avoid agentdojo? AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. ### When should I avoid judgeval? If you are looking for a tool focused solely on the theoretical aspects of AI development without practical, continuous improvement methodologies. You require a solution that only supports evaluation metrics and does not offer integrated environment data support, diverging from Judgeval’s comprehensive approach. ### Is agentdojo or judgeval more popular on GitHub? judgeval has more GitHub stars (1,047 vs 716). Stars measure visibility, not whether either tool fits your constraints. ### Are agentdojo and judgeval open source? Yes - both are open-source projects on GitHub (agentdojo: MIT, judgeval: Apache-2.0). ### Where can I find alternatives to agentdojo or judgeval? GraphCanon lists graph-backed alternatives at [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) and [judgeval alternatives](/tools/judgmentlabs-judgeval/alternatives) ([agentdojo markdown twin](/tools/ethz-spylab-agentdojo/alternatives.md), [judgeval markdown twin](/tools/judgmentlabs-judgeval/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/ethz-spylab-agentdojo-vs-judgmentlabs-judgeval.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agentdojo or judgeval? agentdojo: Steady. judgeval: Very active. 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 agentdojo and judgeval? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust); [judgeval trust report](/tools/judgmentlabs-judgeval/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=ethz-spylab-agentdojo`](/api/graphcanon/graph?tool=ethz-spylab-agentdojo) - 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/_