Comparison
jailbreak-evaluation vs AutoDefense
Verdict
Pick jailbreak-evaluation if jailbreak-evaluation is a Python package aimed at evaluating if AI models have been jailbroken by generating outputs that diverge from expected programming; pick AutoDefense if autoDefense uses a multi-agent framework to mitigate jailbreak attacks on LLMs, installed via Python.
Markdown twin · jailbreak-evaluation alternatives · AutoDefense alternatives
GraphCanon updated Oct 5, 2026
10views this month
vs
Trust & integrity
| Signal | jailbreak-evaluation | AutoDefense |
|---|---|---|
| Maintenance | Dormant (699d since push) As of Oct 5, 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 5, 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
- jailbreak-evaluation
- Python package for language model jailbreak evaluation
- AutoDefense
- Multi-Agent LLM Defense against Jailbreak Attacks
Stars
- jailbreak-evaluation
- 28
- AutoDefense
- 69
Forks
- jailbreak-evaluation
- 8
- AutoDefense
- 20
Open issues
- jailbreak-evaluation
- 0
- AutoDefense
- 1
Language
- jailbreak-evaluation
- Python
- AutoDefense
- Python
Adopt for
- jailbreak-evaluation
- jailbreak-evaluation is a Python package aimed at evaluating if AI models have been jailbroken by generating outputs that diverge from expected programming.
- AutoDefense
- AutoDefense uses a multi-agent framework to mitigate jailbreak attacks on LLMs, installed via Python.
Persona
- jailbreak-evaluation
- -
- AutoDefense
- -
Runtime
- jailbreak-evaluation
- -
- AutoDefense
- -
License
- jailbreak-evaluation
- Apache-2.0
- AutoDefense
- MIT
Last pushed
- jailbreak-evaluation
- Nov 4, 2024
- AutoDefense
- Sep 21, 2026
Categories
- jailbreak-evaluation
- Evaluation & Observability
- AutoDefense
- AI Agents, Evaluation & Observability
Trust and health
Maintenance
- jailbreak-evaluation
- Dormant (18%)
- AutoDefense
- Active (82%)
Days since push
- jailbreak-evaluation
- 699d
- AutoDefense
- 13d
Open issues (now)
- jailbreak-evaluation
- 0
- AutoDefense
- 1
Stars delta
- jailbreak-evaluation
- 0 (30d)
- AutoDefense
- +1 (30d)
Owner type
- jailbreak-evaluation
- Organization
- AutoDefense
- User
Full report
- jailbreak-evaluation
- Trust report
- AutoDefense
- Trust report
Shared compatibility
- Python · jailbreak-evaluation: Python runtime · AutoDefense: Python runtime
Choose jailbreak-evaluation if…
- License: jailbreak-evaluation is Apache-2.0, AutoDefense is MIT.
- Requirements: The tool depends on having PyTorch and FastChat installed; An API key from the OpenAI Platform is required for full functionality.
- Tags unique to jailbreak-evaluation: ai-safety, evaluation tools, jailbreaks, language models.
- When you need to assess whether an AI model can be manipulated to produce unpredictable or unintended outcomes through specific inputs, such as jailbreaking.
When NOT to use jailbreak-evaluation
- If your project does not involve assessing the security or integrity of how an AI model responds to manipulative input techniques designed to exploit design weaknesses.
- When you do not need dependencies on specific frameworks like PyTorch and FastChat, as jailbreak-evaluation requires these without automating their installation.
Choose AutoDefense if…
- License: AutoDefense is MIT, jailbreak-evaluation is Apache-2.0.
- Tags unique to AutoDefense: defense-mechanism, jailbreak prevention, large-language-models, llm-defense.
- Also covers AI Agents.
- Implementing robust defenses for enterprise-level AI projects with high-security requirements
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 (controllability/jailbreak-evaluation) · observed Oct 5, 2026
- GitHub forks (controllability/jailbreak-evaluation) · observed Oct 5, 2026
- Last push (controllability/jailbreak-evaluation) · observed Nov 4, 2024
- License file (Apache-2.0) · observed Oct 5, 2026
- Decision facts (enrichment) · observed Jul 17, 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: jailbreak-evaluation 28 · AutoDefense 69 (synced Oct 5, 2026).
Common questions
- What is the difference between jailbreak-evaluation and AutoDefense?
- jailbreak-evaluation: Python package for language model jailbreak evaluation. AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks. See the comparison table for live GitHub stats and shared categories.
- When should I choose jailbreak-evaluation over AutoDefense?
- Choose jailbreak-evaluation over AutoDefense when License: jailbreak-evaluation is Apache-2.0, AutoDefense is MIT; Requirements: The tool depends on having PyTorch and FastChat installed; An API key from the OpenAI Platform is required for full functionality; Tags unique to jailbreak-evaluation: ai-safety, evaluation tools, jailbreaks, language models; When you need to assess whether an AI model can be manipulated to produce unpredictable or unintended outcomes through specific inputs, such as jailbreaking.
- When should I choose AutoDefense over jailbreak-evaluation?
- Choose AutoDefense over jailbreak-evaluation when License: AutoDefense is MIT, jailbreak-evaluation is Apache-2.0; Tags unique to AutoDefense: defense-mechanism, jailbreak prevention, large-language-models, llm-defense; Also covers AI Agents; Implementing robust defenses for enterprise-level AI projects with high-security requirements.
- When should I avoid jailbreak-evaluation?
- If your project does not involve assessing the security or integrity of how an AI model responds to manipulative input techniques designed to exploit design weaknesses. When you do not need dependencies on specific frameworks like PyTorch and FastChat, as jailbreak-evaluation requires these without automating their installation.
- 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 jailbreak-evaluation or AutoDefense more popular on GitHub?
- AutoDefense has more GitHub stars (69 vs 28). Stars measure visibility, not whether either tool fits your constraints.
- Are jailbreak-evaluation and AutoDefense open source?
- Yes - both are open-source projects on GitHub (jailbreak-evaluation: Apache-2.0, AutoDefense: MIT).
- Where can I find alternatives to jailbreak-evaluation or AutoDefense?
- GraphCanon lists graph-backed alternatives at jailbreak-evaluation alternatives and AutoDefense alternatives (jailbreak-evaluation 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, jailbreak-evaluation or AutoDefense?
- jailbreak-evaluation: Dormant. 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 jailbreak-evaluation and AutoDefense?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: jailbreak-evaluation trust report; AutoDefense trust report.