--- title: "agentdojo vs Aegis" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/ethz-spylab-agentdojo-vs-justin0504-aegis" tools: ["ethz-spylab-agentdojo", "justin0504-aegis"] --- # agentdojo vs Aegis *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 Aegis if aegis provides runtime policy enforcement for AI agents with cryptographic audit trails and human-in-the-loop approvals, supporting zero-code deployment switches suited for various compliance needs. [agentdojo](https://agentdojo.spylab.ai/) reports 802 GitHub stars, 205 forks, and 51 open issues, last pushed Jun 2, 2026. [Aegis](https://github.com/Justin0504/Aegis) has 340 stars, 37 forks, and 3 open issues, last pushed Sep 6, 2026. Figures are from public GitHub metadata via [agentdojo's repository](https://github.com/ethz-spylab/agentdojo) and [Aegis's repository](https://github.com/Justin0504/Aegis). | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [Aegis](/tools/justin0504-aegis.md) | | --- | --- | --- | | Tagline | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | Runtime policy enforcement for AI agents with cryptographic audit trail and human-in-the-loop approvals. | | Stars | 802 | 340 | | Forks | 205 | 37 | | Open issues | 51 | 3 | | Language | Python | TypeScript | | Adopt for | AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. | Aegis provides runtime policy enforcement for AI agents with cryptographic audit trails and human-in-the-loop approvals, supporting zero-code deployment switches suited for various compliance needs. | | 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) | [Aegis](/tools/justin0504-aegis.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Very active (96%) | | Days since push | 94d | 4d | | Open issues (now) | 51 | 3 | | Stars delta | +86 (30d) | -27 (30d) | | Open issues delta | +10 (30d) | 0 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | [trust report](/tools/justin0504-aegis/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: Aegis - **Adopt for:** Aegis provides runtime policy enforcement for AI agents with cryptographic audit trails and human-in-the-loop approvals, supporting zero-code deployment switches suited for various compliance needs. ## Choose when ### Choose agentdojo if… - agentdojo is primarily Python; Aegis is TypeScript. - 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 Aegis if… - Aegis is primarily TypeScript; agentdojo is Python. - Tags unique to Aegis: ai-safety, anthropic, audit-trail, llm-observability. - Aegis ships Docker support for self-hosted deployment. - You need cryptographic assurance of the audit trail to meet high-security standards. ## 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 Aegis - The project does not require a zero-code deployment switch and can manage changes directly in the codebase. - Minimal regulatory requirements mean that elaborate configurations like Aegis's strict retention policies are unnecessary. ## Common questions ### What is the difference between agentdojo and Aegis? agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. Aegis: Runtime policy enforcement for AI agents with cryptographic audit trail and human-in-the-loop approvals.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agentdojo over Aegis? Choose agentdojo over Aegis when agentdojo is primarily Python; Aegis is TypeScript; 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 Aegis over agentdojo? Choose Aegis over agentdojo when Aegis is primarily TypeScript; agentdojo is Python; Tags unique to Aegis: ai-safety, anthropic, audit-trail, llm-observability; Aegis ships Docker support for self-hosted deployment; You need cryptographic assurance of the audit trail to meet high-security standards. ### 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 Aegis? The project does not require a zero-code deployment switch and can manage changes directly in the codebase. Minimal regulatory requirements mean that elaborate configurations like Aegis's strict retention policies are unnecessary. ### Is agentdojo or Aegis more popular on GitHub? agentdojo has more GitHub stars (802 vs 340). Stars measure visibility, not whether either tool fits your constraints. ### Are agentdojo and Aegis open source? Yes - both are open-source projects on GitHub (agentdojo: MIT, Aegis: MIT). ### Where can I find alternatives to agentdojo or Aegis? GraphCanon lists graph-backed alternatives at [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) and [Aegis alternatives](/tools/justin0504-aegis/alternatives) ([agentdojo markdown twin](/tools/ethz-spylab-agentdojo/alternatives.md), [Aegis markdown twin](/tools/justin0504-aegis/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-justin0504-aegis.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agentdojo or Aegis? agentdojo: Slowing. Aegis: 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 Aegis? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust); [Aegis trust report](/tools/justin0504-aegis/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/_