Comparison
agentdojo vs AutoDefense
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 AutoDefense if autoDefense uses a multi-agent framework to mitigate jailbreak attacks on LLMs, installed via Python.
Markdown twin · agentdojo alternatives · AutoDefense alternatives
GraphCanon updated Oct 6, 2026
17views this month
vs
Trust & integrity
| Signal | agentdojo | AutoDefense |
|---|---|---|
| Maintenance | Slowing (125d since push) As of Oct 6, 2026 · github_public_v1 | Active (13d since push) As of Oct 5, 2026 · github_public_v1 |
| Provenance | Not a fork · Organization account As of Oct 6, 2026 · github_public_v1 | Not a fork · Personal account As of Oct 5, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- agentdojo
- A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- AutoDefense
- Multi-Agent LLM Defense against Jailbreak Attacks
Stars
- agentdojo
- 893
- AutoDefense
- 69
Forks
- agentdojo
- 235
- AutoDefense
- 20
Open issues
- agentdojo
- 72
- AutoDefense
- 1
Language
- agentdojo
- Python
- AutoDefense
- Python
Adopt for
- agentdojo
- AgentDojo serves as a benchmarking environment to evaluate security attacks, like prompt injection, and defenses for Large Language Model (LLM) agents.
- AutoDefense
- AutoDefense uses a multi-agent framework to mitigate jailbreak attacks on LLMs, installed via Python.
Persona
- agentdojo
- -
- AutoDefense
- -
Runtime
- agentdojo
- -
- AutoDefense
- -
License
- agentdojo
- MIT
- AutoDefense
- MIT
Last pushed
- agentdojo
- Jun 2, 2026
- AutoDefense
- Sep 21, 2026
Categories
- agentdojo
- AI Agents, Evaluation & Observability
- AutoDefense
- AI Agents, Evaluation & Observability
Trust and health
Maintenance
- agentdojo
- Slowing (36%)
- AutoDefense
- Active (82%)
Days since push
- agentdojo
- 125d
- AutoDefense
- 13d
Open issues (now)
- agentdojo
- 72
- AutoDefense
- 1
Stars delta
- agentdojo
- +91 (30d)
- AutoDefense
- +1 (30d)
Open issues delta
- agentdojo
- +21 (30d)
- AutoDefense
- 0 (30d)
Owner type
- agentdojo
- Organization
- AutoDefense
- User
Full report
- agentdojo
- Trust report
- AutoDefense
- Trust report
Shared compatibility
- Python · agentdojo: Python runtime · AutoDefense: Python runtime
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, prompt-injection.
- 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 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.
Choose AutoDefense if…
- Tags unique to AutoDefense: defense-mechanism, jailbreak prevention, llm-defense, multi-agent.
- Implementing robust defenses for enterprise-level AI projects with high-security requirements
- More recently updated (last pushed Sep 21, 2026).
When NOT to use AutoDefense
- Projects requiring light-weight solutions where multi-agent systems might introduce complexity overhead
- Environments without access to Python and its ecosystem, as AutoDefense depends on specific Python packages
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (ethz-spylab/agentdojo) · observed Oct 6, 2026
- GitHub forks (ethz-spylab/agentdojo) · observed Oct 6, 2026
- Last push (ethz-spylab/agentdojo) · observed Jun 2, 2026
- License file (MIT) · observed Oct 6, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (XHMY/AutoDefense) · observed Oct 5, 2026
- GitHub forks (XHMY/AutoDefense) · observed Oct 5, 2026
- Last push (XHMY/AutoDefense) · observed Sep 21, 2026
- License file (MIT) · observed Oct 5, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: agentdojo 893 · AutoDefense 69 (synced Oct 6, 2026).
Common questions
- What is the difference between agentdojo and AutoDefense?
- agentdojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks. See the comparison table for live GitHub stats and shared categories.
- When should I choose agentdojo over AutoDefense?
- Choose agentdojo over AutoDefense 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, prompt-injection; 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 AutoDefense over agentdojo?
- Choose AutoDefense over agentdojo when Tags unique to AutoDefense: defense-mechanism, jailbreak prevention, llm-defense, multi-agent; Implementing robust defenses for enterprise-level AI projects with high-security requirements; More recently updated (last pushed Sep 21, 2026).
- 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 AutoDefense?
- Projects requiring light-weight solutions where multi-agent systems might introduce complexity overhead Environments without access to Python and its ecosystem, as AutoDefense depends on specific Python packages
- Is agentdojo or AutoDefense more popular on GitHub?
- agentdojo has more GitHub stars (893 vs 69). Stars measure visibility, not whether either tool fits your constraints.
- Are agentdojo and AutoDefense open source?
- Yes - both are open-source projects on GitHub (agentdojo: MIT, AutoDefense: MIT).
- Where can I find alternatives to agentdojo or AutoDefense?
- GraphCanon lists graph-backed alternatives at agentdojo alternatives and AutoDefense alternatives (agentdojo markdown twin, AutoDefense markdown twin), 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 mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, agentdojo or AutoDefense?
- agentdojo: Slowing. AutoDefense: 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 AutoDefense?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: agentdojo trust report; AutoDefense trust report.