--- title: "agentdojo vs ReNeLLM" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/ethz-spylab-agentdojo-vs-njunlp-renellm" tools: ["ethz-spylab-agentdojo", "njunlp-renellm"] --- # agentdojo vs ReNeLLM *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 ReNeLLM if reNeLLM is an implementation of generalized nested jailbreak prompts targeting large language models such as gpt-3.5-turbo and claude-v2. [agentdojo](https://agentdojo.spylab.ai/) reports 716 GitHub stars, 188 forks, and 41 open issues, last pushed Jun 2, 2026. [ReNeLLM](https://github.com/NJUNLP/ReNeLLM) has 163 stars, 17 forks, and 0 open issues, last pushed Sep 2, 2025. Figures are from public GitHub metadata via [agentdojo's repository](https://github.com/ethz-spylab/agentdojo) and [ReNeLLM's repository](https://github.com/NJUNLP/ReNeLLM). | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [ReNeLLM](/tools/njunlp-renellm.md) | | --- | --- | --- | | Tagline | A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents | Implementation of generalized nested jailbreak prompts targeting large language models. | | Stars | 716 | 163 | | Forks | 188 | 17 | | Open issues | 41 | 0 | | 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. | ReNeLLM is an implementation of generalized nested jailbreak prompts targeting large language models such as gpt-3.5-turbo and claude-v2. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | AI Agents, Evaluation & Observability | Evaluation & Observability, Inference & Serving | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agentdojo](/tools/ethz-spylab-agentdojo.md) | [ReNeLLM](/tools/njunlp-renellm.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Slowing (36%) | | Days since push | 63d | 336d | | Open issues (now) | 41 | 0 | | Full report | [trust report](/tools/ethz-spylab-agentdojo/trust.md) | [trust report](/tools/njunlp-renellm/trust.md) | ## Shared compatibility - **Python**: [agentdojo](/tools/ethz-spylab-agentdojo.md) - Python runtime; [ReNeLLM](/tools/njunlp-renellm.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: ReNeLLM - **Adopt for:** ReNeLLM is an implementation of generalized nested jailbreak prompts targeting large language models such as gpt-3.5-turbo and claude-v2. ## 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: benchmark, large language models, prompt-injection, security. - Also covers AI Agents. - AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents. ### Choose ReNeLLM if… - Tags unique to ReNeLLM: api interaction, jailbreak prompts, language model evaluation, model reliability assessment. - Also covers Inference & Serving. - When you aim to evaluate the susceptibility of LLMs like gpt-3.5-turbo and claude-v2 to deception or jailbroken prompts. ## 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 ReNeLLM - When you wish to develop applications that strictly adhere to ethical guidelines and do not involve the testing of harmful prompts. - If your focus is on building production-ready LLM-based services without interest in evaluating security or adversarial aspects of these models. ## Common questions ### What is the difference between agentdojo and ReNeLLM? agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. ReNeLLM: Implementation of generalized nested jailbreak prompts targeting large language models.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agentdojo over ReNeLLM? Choose agentdojo over ReNeLLM 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: benchmark, large language models, prompt-injection, security; Also covers AI Agents; 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 ReNeLLM over agentdojo? Choose ReNeLLM over agentdojo when Tags unique to ReNeLLM: api interaction, jailbreak prompts, language model evaluation, model reliability assessment; Also covers Inference & Serving; When you aim to evaluate the susceptibility of LLMs like gpt-3.5-turbo and claude-v2 to deception or jailbroken prompts. ### 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 ReNeLLM? When you wish to develop applications that strictly adhere to ethical guidelines and do not involve the testing of harmful prompts. If your focus is on building production-ready LLM-based services without interest in evaluating security or adversarial aspects of these models. ### Is agentdojo or ReNeLLM more popular on GitHub? agentdojo has more GitHub stars (716 vs 163). Stars measure visibility, not whether either tool fits your constraints. ### Are agentdojo and ReNeLLM open source? Yes - both are open-source projects on GitHub (agentdojo: MIT, ReNeLLM: MIT). ### Where can I find alternatives to agentdojo or ReNeLLM? GraphCanon lists graph-backed alternatives at [agentdojo alternatives](/tools/ethz-spylab-agentdojo/alternatives) and [ReNeLLM alternatives](/tools/njunlp-renellm/alternatives) ([agentdojo markdown twin](/tools/ethz-spylab-agentdojo/alternatives.md), [ReNeLLM markdown twin](/tools/njunlp-renellm/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-njunlp-renellm.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agentdojo or ReNeLLM? agentdojo: Steady. ReNeLLM: Slowing. 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 ReNeLLM? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agentdojo trust report](/tools/ethz-spylab-agentdojo/trust); [ReNeLLM trust report](/tools/njunlp-renellm/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/_