--- title: "agentdojo vs WeaveBench" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/ethz-spylab-agentdojo-vs-weavebench-weavebench" tools: ["ethz-spylab-agentdojo", "weavebench-weavebench"] --- # agentdojo vs WeaveBench *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 WeaveBench if weaveBench is designed for evaluating computer-use agents that integrate both GUI and CLI interactions in real-world scenarios across various work domains. [agentdojo](https://agentdojo.spylab.ai/) reports 716 GitHub stars, 188 forks, and 41 open issues, last pushed Jun 2, 2026. [WeaveBench](https://weavebench.github.io) has 157 stars, 1 forks, and 4 open issues, last pushed Jul 22, 2026. Figures are from public GitHub metadata via [agentdojo's repository](https://github.com/ethz-spylab/agentdojo) and [WeaveBench's repository](https://github.com/weavebench/WeaveBench). | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [WeaveBench](/tools/weavebench-weavebench.md) | | --- | --- | --- | | Tagline | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | A Long-Horizon Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces | | Stars | 716 | 157 | | Forks | 188 | 1 | | Open issues | 41 | 4 | | 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. | WeaveBench is designed for evaluating computer-use agents that integrate both GUI and CLI interactions in real-world scenarios across various work domains. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | 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) | [WeaveBench](/tools/weavebench-weavebench.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 63d | 6d | | Open issues (now) | 41 | 4 | | Full report | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | [trust report](/tools/weavebench-weavebench/trust.md) | ## 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: WeaveBench - **Adopt for:** WeaveBench is designed for evaluating computer-use agents that integrate both GUI and CLI interactions in real-world scenarios across various work domains. ## Choose when ### Choose agentdojo if… - 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 WeaveBench if… - Tags unique to WeaveBench: agent-as-judge, computer-use-agent, gui-agent, hybrid-interface. - Use WeaveBench if you need to assess agents capable of handling tasks that require intermingling graphical user interface operations with command-line or code-based actions. - More recently updated (last pushed Jul 22, 2026). ## 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 WeaveBench - Avoid WeaveBench if your testing needs do not involve scenarios that require the integration of both GUI and CLI operations. - Do not use it when you are specifically interested only in benchmarking agents designed for single-channel tasks, either strictly CLI-based or purely graphical interface-driven. ## Common questions ### What is the difference between agentdojo and WeaveBench? agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. WeaveBench: A Long-Horizon Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces. See the comparison table for live GitHub stats and shared categories. ### When should I choose agentdojo over WeaveBench? Choose agentdojo over WeaveBench when 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 WeaveBench over agentdojo? Choose WeaveBench over agentdojo when Tags unique to WeaveBench: agent-as-judge, computer-use-agent, gui-agent, hybrid-interface; Use WeaveBench if you need to assess agents capable of handling tasks that require intermingling graphical user interface operations with command-line or code-based actions; More recently updated (last pushed Jul 22, 2026). ### 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 WeaveBench? Avoid WeaveBench if your testing needs do not involve scenarios that require the integration of both GUI and CLI operations. Do not use it when you are specifically interested only in benchmarking agents designed for single-channel tasks, either strictly CLI-based or purely graphical interface-driven. ### Is agentdojo or WeaveBench more popular on GitHub? agentdojo has more GitHub stars (716 vs 157). Stars measure visibility, not whether either tool fits your constraints. ### Are agentdojo and WeaveBench open source? Yes - both are open-source projects on GitHub (agentdojo: MIT, WeaveBench: MIT). ### Where can I find alternatives to agentdojo or WeaveBench? GraphCanon lists graph-backed alternatives at [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) and [WeaveBench alternatives](/tools/weavebench-weavebench/alternatives) ([agentdojo markdown twin](/tools/ethz-spylab-agentdojo/alternatives.md), [WeaveBench markdown twin](/tools/weavebench-weavebench/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-weavebench-weavebench.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agentdojo or WeaveBench? agentdojo: Steady. WeaveBench: 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 WeaveBench? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust); [WeaveBench trust report](/tools/weavebench-weavebench/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/_