---
title: "llm-attacks vs AutoGPT"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/llm-attacks-llm-attacks-vs-significant-gravitas-autogpt"
tools: ["llm-attacks-llm-attacks", "significant-gravitas-autogpt"]
---

# llm-attacks vs AutoGPT

*GraphCanon updated Jul 11, 2026*

## Verdict

Pick llm-attacks when license: llm-attacks is MIT, AutoGPT is Other; pick AutoGPT when license: AutoGPT is Other, llm-attacks is MIT.

[llm-attacks](https://llm-attacks.org/) reports 4.7k GitHub stars, 631 forks, and 70 open issues, last pushed Aug 2, 2024. [AutoGPT](https://agpt.co) has 185k stars, 46k forks, and 494 open issues, last pushed Jul 11, 2026. Figures are from public GitHub metadata via [llm-attacks's repository](https://github.com/llm-attacks/llm-attacks) and [AutoGPT's repository](https://github.com/Significant-Gravitas/AutoGPT).

| | [llm-attacks](/tools/llm-attacks-llm-attacks.md) | [AutoGPT](/tools/significant-gravitas-autogpt.md) |
| --- | --- | --- |
| Tagline | Universal and Transferable Attacks on Aligned Language Models | AutoGPT is the vision of accessible AI for everyone, to use and to build on. |
| Stars | 4,735 | 185,464 |
| Forks | 631 | 46,111 |
| Open issues | 70 | 494 |
| Language | Python | Python |
| Adopt for | - | AutoGPT is a Python-based tool for creating accessible autonomous AI agents that can leverage various LLM APIs including OpenAI's GPT and Anthropic's Claude. |
| Persona | - | - |
| Runtime | - | - |
| License | MIT | Other |
| Categories | LLM Frameworks | AI Agents, LLM Frameworks |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [llm-attacks](/tools/llm-attacks-llm-attacks.md) | [AutoGPT](/tools/significant-gravitas-autogpt.md) |
| --- | --- | --- |
| Maintenance | Dormant (18%) | Very active (96%) |
| Days since push | 708d | 0d |
| Open issues (now) | 70 | 494 |
| Security scan | 58 low (58 low) | No lockfile |
| Full report | [trust report](/tools/llm-attacks-llm-attacks/trust.md) | [trust report](/tools/significant-gravitas-autogpt/trust.md) |

## Decision facts: AutoGPT

- **Adopt for:** AutoGPT is a Python-based tool for creating accessible autonomous AI agents that can leverage various LLM APIs including OpenAI's GPT and Anthropic's Claude.

## Choose when

### Choose llm-attacks if…

- License: llm-attacks is MIT, AutoGPT is Other.
- Tags unique to llm-attacks: python.
- Leaner open-issue backlog (70).

### Choose AutoGPT if…

- License: AutoGPT is Other, llm-attacks is MIT.
- Tags unique to AutoGPT: agentic-ai, agents, ai, artificial-intelligence.
- Also covers AI Agents.
- When you need to rapidly prototype or deploy an autonomous agent using existing language models without deep AI expertise.

## When NOT to use llm-attacks

- Last GitHub push was 709 days ago (dormant maintenance, Aug 2, 2024). Validate activity before betting a new project on llm-attacks.
- LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.

## When NOT to use AutoGPT

- Avoid if you require absolute control over the underlying AI infrastructure and APIs used by your autonomous agents, as AutoGPT imposes its own framework.
- If your project demands proprietary or specialized models that aren't supported by AutoGPT's API ecosystem (e.g., custom TensorFlow or PyTorch models), consider other tools.

## Common questions

### What is the difference between llm-attacks and AutoGPT?

llm-attacks: Universal and Transferable Attacks on Aligned Language Models. AutoGPT: AutoGPT is the vision of accessible AI for everyone, to use and to build on.. See the comparison table for live GitHub stats and shared categories.

### When should I choose llm-attacks over AutoGPT?

Choose llm-attacks over AutoGPT when License: llm-attacks is MIT, AutoGPT is Other; Tags unique to llm-attacks: python; Leaner open-issue backlog (70).

### When should I choose AutoGPT over llm-attacks?

Choose AutoGPT over llm-attacks when License: AutoGPT is Other, llm-attacks is MIT; Tags unique to AutoGPT: agentic-ai, agents, ai, artificial-intelligence; Also covers AI Agents; When you need to rapidly prototype or deploy an autonomous agent using existing language models without deep AI expertise.

### When should I avoid llm-attacks?

Last GitHub push was 709 days ago (dormant maintenance, Aug 2, 2024). Validate activity before betting a new project on llm-attacks. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves.

### When should I avoid AutoGPT?

Avoid if you require absolute control over the underlying AI infrastructure and APIs used by your autonomous agents, as AutoGPT imposes its own framework. If your project demands proprietary or specialized models that aren't supported by AutoGPT's API ecosystem (e.g., custom TensorFlow or PyTorch models), consider other tools.

### Is llm-attacks or AutoGPT more popular on GitHub?

AutoGPT has more GitHub stars (185,464 vs 4,735). Stars measure visibility, not whether either tool fits your constraints.

### Are llm-attacks and AutoGPT open source?

Yes - both are open-source projects on GitHub (llm-attacks: MIT, AutoGPT: Other).

### Where can I find alternatives to llm-attacks or AutoGPT?

GraphCanon lists graph-backed alternatives at [llm-attacks alternatives](/tools/llm-attacks-llm-attacks/alternatives) and [AutoGPT alternatives](/tools/significant-gravitas-autogpt/alternatives) ([llm-attacks markdown twin](/tools/llm-attacks-llm-attacks/alternatives.md), [AutoGPT markdown twin](/tools/significant-gravitas-autogpt/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/llm-attacks-llm-attacks-vs-significant-gravitas-autogpt.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, llm-attacks or AutoGPT?

llm-attacks: Dormant. AutoGPT: 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 llm-attacks and AutoGPT?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [llm-attacks trust report](/tools/llm-attacks-llm-attacks/trust); [AutoGPT trust report](/tools/significant-gravitas-autogpt/trust).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=llm-attacks-llm-attacks`](/api/graphcanon/graph?tool=llm-attacks-llm-attacks)
- 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/_