--- title: "agent-zero vs agentdojo" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/agent0ai-agent-zero-vs-ethz-spylab-agentdojo" tools: ["agent0ai-agent-zero", "ethz-spylab-agentdojo"] --- # agent-zero vs agentdojo *GraphCanon updated Jul 12, 2026* ## Verdict Pick agent-zero if agent-zero is a Python-based autonomous agent framework that uses Docker for deployment and supports integration with LLM providers such as OpenAI Codex via OAuth; pick agentdojo if agentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. [agent-zero](https://agent-zero.ai) reports 18k GitHub stars, 3.7k forks, and 235 open issues, last pushed Jul 10, 2026. [agentdojo](https://agentdojo.spylab.ai/) has 659 stars, 168 forks, and 33 open issues, last pushed Jun 2, 2026. Figures are from public GitHub metadata via [agent-zero's repository](https://github.com/agent0ai/agent-zero) and [agentdojo's repository](https://github.com/ethz-spylab/agentdojo). | | [agent-zero](/tools/agent0ai-agent-zero.md) | [agentdojo](/tools/ethz-spylab-agentdojo.md) | | --- | --- | --- | | Tagline | Agent Zero AI framework | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | | Stars | 18,393 | 659 | | Forks | 3,680 | 168 | | Open issues | 235 | 33 | | Language | Python | Python | | Adopt for | Agent-zero is a Python-based autonomous agent framework that uses Docker for deployment and supports integration with LLM providers such as OpenAI Codex via OAuth. | AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. | | Persona | - | - | | Runtime | - | - | | License | Other | MIT | | Categories | AI Agents, Inference & Serving | AI Agents, Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-zero](/tools/agent0ai-agent-zero.md) | [agentdojo](/tools/ethz-spylab-agentdojo.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Steady (60%) | | Days since push | 0d | 39d | | Open issues (now) | 235 | 33 | | Security scan | 99 low (99 low) | No lockfile | | Full report | [trust report](/tools/agent0ai-agent-zero/trust.md) | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | ## Decision facts: agent-zero - **Pricing:** unknown - The repository does not explicitly state any pricing information. - **Requirements:** Requires Docker; Requires Docker setup and can be configured to leverage existing Docker environments. - **Adopt for:** Agent-zero is a Python-based autonomous agent framework that uses Docker for deployment and supports integration with LLM providers such as OpenAI Codex via OAuth. ## 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. ## Choose when ### Choose agent-zero if… - License: agent-zero is Other, agentdojo is MIT. - Pricing: The repository does not explicitly state any pricing information.. - Requirements: Requires Docker; Requires Docker setup and can be configured to leverage existing Docker environments.. - Tags unique to agent-zero: assistant, zero, linux, autonomous. - Also covers Inference & Serving. - * When setting up agents in SSH sessions, servers, recovery shells, or requiring scriptable installation processes. ### Choose agentdojo if… - License: agentdojo is MIT, agent-zero is Other. - 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: prompt-injection, benchmark, large-language-models, security. - Also covers Evaluation & Observability. - AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. ## When NOT to use agent-zero - * When your deployment environment does not support or require Dockerization for agent operations. - * In scenarios where OAuth-based integration with third-party language model providers is undesirable or impractical. - * For installations that do not align well with the provided `/a0/usr` directory mapping conventions (e.g., specific data directories are required). ## 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. ## Common questions ### What is the difference between agent-zero and agentdojo? agent-zero: Agent Zero AI framework. agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-zero over agentdojo? Choose agent-zero over agentdojo when License: agent-zero is Other, agentdojo is MIT; Pricing: The repository does not explicitly state any pricing information.; Requirements: Requires Docker; Requires Docker setup and can be configured to leverage existing Docker environments.; Tags unique to agent-zero: assistant, zero, linux, autonomous; Also covers Inference & Serving; * When setting up agents in SSH sessions, servers, recovery shells, or requiring scriptable installation processes. ### When should I choose agentdojo over agent-zero? Choose agentdojo over agent-zero when License: agentdojo is MIT, agent-zero is Other; 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: prompt-injection, benchmark, large-language-models, security; Also covers Evaluation & Observability; AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. ### When should I avoid agent-zero? * When your deployment environment does not support or require Dockerization for agent operations. * In scenarios where OAuth-based integration with third-party language model providers is undesirable or impractical. * For installations that do not align well with the provided `/a0/usr` directory mapping conventions (e.g., specific data directories are required). ### 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. ### Is agent-zero or agentdojo more popular on GitHub? agent-zero has more GitHub stars (18,393 vs 659). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-zero and agentdojo open source? Yes - both are open-source projects on GitHub (agent-zero: Other, agentdojo: MIT). ### Where can I find alternatives to agent-zero or agentdojo? GraphCanon lists graph-backed alternatives at [agent-zero alternatives](/tools/agent0ai-agent-zero/alternatives) and [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) ([agent-zero markdown twin](/tools/agent0ai-agent-zero/alternatives.md), [agentdojo markdown twin](/tools/ethz-spylab-agentdojo/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/agent0ai-agent-zero-vs-ethz-spylab-agentdojo.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-zero or agentdojo? agent-zero: Very active. agentdojo: 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 agent-zero and agentdojo? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-zero trust report](/tools/agent0ai-agent-zero/trust); [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=agent0ai-agent-zero`](/api/graphcanon/graph?tool=agent0ai-agent-zero) - 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/_