--- title: "agentdojo vs agentic-vbench" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/ethz-spylab-agentdojo-vs-philolabs-agentic-vbench" tools: ["ethz-spylab-agentdojo", "philolabs-agentic-vbench"] --- # agentdojo vs agentic-vbench *GraphCanon updated Sep 20, 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 agentic-vbench if agenticVBench evaluates AI agents' real-world post-production capabilities with specific task prompts for activities like audio restoration. [agentdojo](https://agentdojo.spylab.ai/) reports 802 GitHub stars, 205 forks, and 51 open issues, last pushed Jun 2, 2026. [agentic-vbench](https://agenticvbench.com/) has 96 stars, 27 forks, and 37 open issues, last pushed Sep 2, 2026. Figures are from public GitHub metadata via [agentdojo's repository](https://github.com/ethz-spylab/agentdojo) and [agentic-vbench's repository](https://github.com/PhiloLabs/agentic-vbench). | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [agentic-vbench](/tools/philolabs-agentic-vbench.md) | | --- | --- | --- | | Tagline | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | A benchmark for evaluating AI agents in performing real-world post-production tasks like audio and video editing. | | Stars | 802 | 96 | | Forks | 205 | 27 | | Open issues | 51 | 37 | | 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. | AgenticVBench evaluates AI agents' real-world post-production capabilities with specific task prompts for activities like audio restoration. | | 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) | [agentic-vbench](/tools/philolabs-agentic-vbench.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Very active (96%) | | Days since push | 94d | 6d | | Open issues (now) | 51 | 37 | | Stars delta | +86 (30d) | +14 (30d) | | Open issues delta | +10 (30d) | -20 (30d) | | Full report | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | [trust report](/tools/philolabs-agentic-vbench/trust.md) | ## Shared compatibility - **Python**: [agentdojo](/tools/ethz-spylab-agentdojo.md) - Python runtime; [agentic-vbench](/tools/philolabs-agentic-vbench.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: agentic-vbench - **Requirements:** Requires Docker; Install via scripts provided in the repository.; Python virtual environment setup for reproducibility. - **Adopt for:** AgenticVBench evaluates AI agents' real-world post-production capabilities with specific task prompts for activities like audio restoration. ## Choose when ### Choose agentdojo if… - License: agentdojo is MIT, agentic-vbench 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: 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 agentic-vbench if… - License: agentic-vbench is Apache-2.0, agentdojo is MIT. - Requirements: Requires Docker; Install via scripts provided in the repository.; Python virtual environment setup for reproducibility.. - Tags unique to agentic-vbench: ai-agents, harbor, llm-evaluation, video-editing. - When you need to benchmark the performance of AI agents in handling specialized tasks such as audio and video editing that require precise restorative actions. ## When NOT to use agentdojo - Last GitHub push was Jun 2, 2026 (slowing maintenance). Validate activity before betting a new project on 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 agentic-vbench - When the focus is on generic performance evaluations rather than on real-world, task-specific benchmarks that assess handling complex post-production scenarios. - If your budget or timeline cannot accommodate a per-task wall clock time of ~10 minutes and cost ranging from $0.10 to $2 based on agent token usage. ## Common questions ### What is the difference between agentdojo and agentic-vbench? agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. agentic-vbench: A benchmark for evaluating AI agents in performing real-world post-production tasks like audio and video editing.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agentdojo over agentic-vbench? Choose agentdojo over agentic-vbench when License: agentdojo is MIT, agentic-vbench 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: 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 agentic-vbench over agentdojo? Choose agentic-vbench over agentdojo when License: agentic-vbench is Apache-2.0, agentdojo is MIT; Requirements: Requires Docker; Install via scripts provided in the repository.; Python virtual environment setup for reproducibility.; Tags unique to agentic-vbench: ai-agents, harbor, llm-evaluation, video-editing; When you need to benchmark the performance of AI agents in handling specialized tasks such as audio and video editing that require precise restorative actions. ### When should I avoid agentdojo? Last GitHub push was Jun 2, 2026 (slowing maintenance). Validate activity before betting a new project on 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 agentic-vbench? When the focus is on generic performance evaluations rather than on real-world, task-specific benchmarks that assess handling complex post-production scenarios. If your budget or timeline cannot accommodate a per-task wall clock time of ~10 minutes and cost ranging from $0.10 to $2 based on agent token usage. ### Is agentdojo or agentic-vbench more popular on GitHub? agentdojo has more GitHub stars (802 vs 96). Stars measure visibility, not whether either tool fits your constraints. ### Are agentdojo and agentic-vbench open source? Yes - both are open-source projects on GitHub (agentdojo: MIT, agentic-vbench: Apache-2.0). ### Where can I find alternatives to agentdojo or agentic-vbench? GraphCanon lists graph-backed alternatives at [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) and [agentic-vbench alternatives](/tools/philolabs-agentic-vbench/alternatives) ([agentdojo markdown twin](/tools/ethz-spylab-agentdojo/alternatives.md), [agentic-vbench markdown twin](/tools/philolabs-agentic-vbench/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-philolabs-agentic-vbench.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agentdojo or agentic-vbench? agentdojo: Slowing. agentic-vbench: 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 agentic-vbench? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust); [agentic-vbench trust report](/tools/philolabs-agentic-vbench/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/_