Comparison
llm-self-defense vs AutoDefense
Verdict
Pick llm-self-defense if mitigates harmful content generation via self-examination by LLM outputs without fine-tuning; pick AutoDefense if autoDefense uses a multi-agent framework to mitigate jailbreak attacks on LLMs, installed via Python.
Markdown twin · llm-self-defense alternatives · AutoDefense alternatives
GraphCanon updated 2w
vs
Trust & integrity
| Signal | llm-self-defense | AutoDefense |
|---|---|---|
| Maintenance | Dormant (805d since push) As of 2w · github_public_v1 | Slowing (201d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Organization account As of 2w · github_public_v1 | Not a fork · Personal account As of 2w · github_public_v1 |
| OSV dependency advisories | Published findings As of 1mo · osv@v1 | No lockfile (source not queried) As of 1mo · 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
- llm-self-defense
- LLM Self Defense: By Self Examination, LLMs know they are being tricked
- AutoDefense
- Multi-Agent LLM Defense against Jailbreak Attacks
Stars
- llm-self-defense
- 52
- AutoDefense
- 68
Forks
- llm-self-defense
- 7
- AutoDefense
- 20
Open issues
- llm-self-defense
- 7
- AutoDefense
- 1
Language
- llm-self-defense
- Python
- AutoDefense
- Python
Adopt for
- llm-self-defense
- Mitigates harmful content generation via self-examination by LLM outputs without fine-tuning.
- AutoDefense
- AutoDefense uses a multi-agent framework to mitigate jailbreak attacks on LLMs, installed via Python.
Persona
- llm-self-defense
- -
- AutoDefense
- -
Runtime
- llm-self-defense
- -
- AutoDefense
- -
License
- llm-self-defense
- BSD-3-Clause
- AutoDefense
- MIT
Last pushed
- llm-self-defense
- May 21, 2024
- AutoDefense
- Jan 15, 2026
Categories
- llm-self-defense
- Evaluation & Observability
- AutoDefense
- AI Agents, Evaluation & Observability
Trust and health
Maintenance
- llm-self-defense
- Dormant (18%)
- AutoDefense
- Slowing (36%)
Days since push
- llm-self-defense
- 805d
- AutoDefense
- 201d
Open issues (now)
- llm-self-defense
- 7
- AutoDefense
- 1
Owner type
- llm-self-defense
- Organization
- AutoDefense
- User
OSV dependency advisories
- llm-self-defense
- Published findings
- AutoDefense
- No lockfile (source not queried)
Full report
- llm-self-defense
- Trust report
- AutoDefense
- Trust report
Shared compatibility
- Python · llm-self-defense: Python runtime · AutoDefense: Python runtime
Choose llm-self-defense if…
- License: llm-self-defense is BSD-3-Clause, AutoDefense is MIT.
- Tags unique to llm-self-defense: adversarial prompts, gpt 3.5, harmful content reduction, llama-2.
- When you need to reduce the success rate of adversarial attacks on text generation.
When NOT to use llm-self-defense
- If real-time performance is critical and additional latency cannot be tolerated.
- In scenarios where API access to both GPT 3.5 and Llama models is not feasible.
Choose AutoDefense if…
- License: AutoDefense is MIT, llm-self-defense is BSD-3-Clause.
- 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 (poloclub/llm-self-defense) · observed Aug 5, 2026
- GitHub forks (poloclub/llm-self-defense) · observed Aug 5, 2026
- Last push (poloclub/llm-self-defense) · observed May 21, 2024
- License file (BSD-3-Clause) · observed Aug 5, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (XHMY/AutoDefense) · observed Aug 5, 2026
- GitHub forks (XHMY/AutoDefense) · observed Aug 5, 2026
- Last push (XHMY/AutoDefense) · observed Jan 15, 2026
- License file (MIT) · observed Aug 5, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: llm-self-defense 52 · AutoDefense 68 (synced Aug 5, 2026).
Common questions
- What is the difference between llm-self-defense and AutoDefense?
- llm-self-defense: LLM Self Defense: By Self Examination, LLMs know they are being tricked. AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks. See the comparison table for live GitHub stats and shared categories.
- When should I choose llm-self-defense over AutoDefense?
- Choose llm-self-defense over AutoDefense when License: llm-self-defense is BSD-3-Clause, AutoDefense is MIT; Tags unique to llm-self-defense: adversarial prompts, gpt 3.5, harmful content reduction, llama-2; When you need to reduce the success rate of adversarial attacks on text generation.
- When should I choose AutoDefense over llm-self-defense?
- Choose AutoDefense over llm-self-defense when License: AutoDefense is MIT, llm-self-defense is BSD-3-Clause; 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 llm-self-defense?
- If real-time performance is critical and additional latency cannot be tolerated. In scenarios where API access to both GPT 3.5 and Llama models is not feasible.
- 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 llm-self-defense or AutoDefense more popular on GitHub?
- AutoDefense has more GitHub stars (68 vs 52). Stars measure visibility, not whether either tool fits your constraints.
- Are llm-self-defense and AutoDefense open source?
- Yes - both are open-source projects on GitHub (llm-self-defense: BSD-3-Clause, AutoDefense: MIT).
- Where can I find alternatives to llm-self-defense or AutoDefense?
- GraphCanon lists graph-backed alternatives at llm-self-defense alternatives and AutoDefense alternatives (llm-self-defense 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, llm-self-defense or AutoDefense?
- llm-self-defense: Dormant. AutoDefense: 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 llm-self-defense and AutoDefense?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: llm-self-defense trust report; AutoDefense trust report.