--- title: "agentdojo vs ClawBench" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/ethz-spylab-agentdojo-vs-tiger-ai-lab-clawbench" tools: ["ethz-spylab-agentdojo", "tiger-ai-lab-clawbench"] --- # agentdojo vs ClawBench *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 ClawBench if clawBench offers an open-source benchmark framework for evaluating browser-based AI agents on real-world online tasks. [agentdojo](https://agentdojo.spylab.ai/) reports 716 GitHub stars, 188 forks, and 41 open issues, last pushed Jun 2, 2026. [ClawBench](https://claw-bench.com) has 532 stars, 30 forks, and 47 open issues, last pushed Jul 28, 2026. Figures are from public GitHub metadata via [agentdojo's repository](https://github.com/ethz-spylab/agentdojo) and [ClawBench's repository](https://github.com/TIGER-AI-Lab/ClawBench). | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [ClawBench](/tools/tiger-ai-lab-clawbench.md) | | --- | --- | --- | | Tagline | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | Open-source benchmark for browser AI agents on daily tasks | | Stars | 716 | 532 | | Forks | 188 | 30 | | Open issues | 41 | 47 | | 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. | ClawBench offers an open-source benchmark framework for evaluating browser-based AI agents on real-world online tasks. | | Persona | - | - | | Runtime | - | - | | License | MIT | ClawBench operates under the Apache-2.0 license, offering a permissive free software license that encourages software reuse and interoperability. | | 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) | [ClawBench](/tools/tiger-ai-lab-clawbench.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 63d | 0d | | Open issues (now) | 41 | 47 | | Full report | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | [trust report](/tools/tiger-ai-lab-clawbench/trust.md) | ## Shared compatibility - **Python**: [agentdojo](/tools/ethz-spylab-agentdojo.md) - Python runtime; [ClawBench](/tools/tiger-ai-lab-clawbench.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: ClawBench - **Requirements:** Requires setup for browser automation tasks within the Chrome environment. - **Adopt for:** ClawBench offers an open-source benchmark framework for evaluating browser-based AI agents on real-world online tasks. - **License detail:** ClawBench operates under the Apache-2.0 license, offering a permissive free software license that encourages software reuse and interoperability. ## Choose when ### Choose agentdojo if… - License: agentdojo is MIT, ClawBench 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 ClawBench if… - License: ClawBench is Apache-2.0, agentdojo is MIT. - Requirements: Requires setup for browser automation tasks within the Chrome environment.. - Tags unique to ClawBench: agent-evaluation, agentic-ai, browser-agent, llm-evaluation. - You are developing a browser AI agent and wish to measure its performance against everyday online activities, as ClawBench specifically simulates these scenarios. ## 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 ClawBench - If your focus is solely on backend server-based AI evaluations without a browser interface involvement, ClawBench will not be the appropriate choice. - For those developing standalone applications or mobile agents, ClawBench’s browser-centric tasks will not reflect their operational capabilities accurately. ## Common questions ### What is the difference between agentdojo and ClawBench? agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. ClawBench: Open-source benchmark for browser AI agents on daily tasks. See the comparison table for live GitHub stats and shared categories. ### When should I choose agentdojo over ClawBench? Choose agentdojo over ClawBench when License: agentdojo is MIT, ClawBench 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 ClawBench over agentdojo? Choose ClawBench over agentdojo when License: ClawBench is Apache-2.0, agentdojo is MIT; Requirements: Requires setup for browser automation tasks within the Chrome environment.; Tags unique to ClawBench: agent-evaluation, agentic-ai, browser-agent, llm-evaluation; You are developing a browser AI agent and wish to measure its performance against everyday online activities, as ClawBench specifically simulates these scenarios. ### 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 ClawBench? If your focus is solely on backend server-based AI evaluations without a browser interface involvement, ClawBench will not be the appropriate choice. For those developing standalone applications or mobile agents, ClawBench’s browser-centric tasks will not reflect their operational capabilities accurately. ### Is agentdojo or ClawBench more popular on GitHub? agentdojo has more GitHub stars (716 vs 532). Stars measure visibility, not whether either tool fits your constraints. ### Are agentdojo and ClawBench open source? Yes - both are open-source projects on GitHub (agentdojo: MIT, ClawBench: Apache-2.0). ### Where can I find alternatives to agentdojo or ClawBench? GraphCanon lists graph-backed alternatives at [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) and [ClawBench alternatives](/tools/tiger-ai-lab-clawbench/alternatives) ([agentdojo markdown twin](/tools/ethz-spylab-agentdojo/alternatives.md), [ClawBench markdown twin](/tools/tiger-ai-lab-clawbench/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-tiger-ai-lab-clawbench.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agentdojo or ClawBench? agentdojo: Steady. ClawBench: 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 ClawBench? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust); [ClawBench trust report](/tools/tiger-ai-lab-clawbench/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/_