---
title: "vigil-llm vs kereva-scanner"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/deadbits-vigil-llm-vs-kereva-dev-kereva-scanner"
tools: ["deadbits-vigil-llm", "kereva-dev-kereva-scanner"]
---

# vigil-llm vs kereva-scanner

*GraphCanon updated Sep 20, 2026*

## Verdict

Pick vigil-llm if vigil-llm is designed for users who need robust security measures to protect against prompt injections and jailbreak attempts in LLMs; pick kereva-scanner if kereva-scanner is a specialized code scanner that assesses AI prompts and interactions with language models for potential security vulnerabilities and performance inefficiencies.

[vigil-llm](https://vigil.deadbits.ai/) reports 496 GitHub stars, 56 forks, and 16 open issues, last pushed Jan 31, 2024. [kereva-scanner](https://kereva.io) has 78 stars, 8 forks, and 3 open issues, last pushed Apr 6, 2025. Figures are from public GitHub metadata via [vigil-llm's repository](https://github.com/deadbits/vigil-llm) and [kereva-scanner's repository](https://github.com/kereva-dev/kereva-scanner).

| | [vigil-llm](/tools/deadbits-vigil-llm.md) | [kereva-scanner](/tools/kereva-dev-kereva-scanner.md) |
| --- | --- | --- |
| Tagline | Detect prompt injections and other risky inputs in LLMs | Code scanner to check for issues in prompts and LLM calls |
| Stars | 496 | 78 |
| Forks | 56 | 8 |
| Open issues | 16 | 3 |
| Language | Python | Python |
| Adopt for | Vigil-llm is designed for users who need robust security measures to protect against prompt injections and jailbreak attempts in LLMs. | kereva-scanner is a specialized code scanner that assesses AI prompts and interactions with language models for potential security vulnerabilities and performance inefficiencies. |
| Persona | - | - |
| Runtime | - | - |
| License | Apache-2.0 | Apache-2.0 |
| Categories | Evaluation & Observability | Developer Tools, Evaluation & Observability |

## Trust and health

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

| | [vigil-llm](/tools/deadbits-vigil-llm.md) | [kereva-scanner](/tools/kereva-dev-kereva-scanner.md) |
| --- | --- | --- |
| Days since push | 962d | 520d |
| Open issues (now) | 16 | 3 |
| Stars delta | +5 (30d) | 0 (30d) |
| Owner type | User | Organization |
| Full report | [trust report](/tools/deadbits-vigil-llm/trust.md) | [trust report](/tools/kereva-dev-kereva-scanner/trust.md) |

## Shared compatibility

- **Python**: [vigil-llm](/tools/deadbits-vigil-llm.md) - Python runtime; [kereva-scanner](/tools/kereva-dev-kereva-scanner.md) - Python runtime

## Decision facts: vigil-llm

- **Adopt for:** Vigil-llm is designed for users who need robust security measures to protect against prompt injections and jailbreak attempts in LLMs.

## Decision facts: kereva-scanner

- **Pricing:** freemium - The tool is free under the Apache-2.0 license but may have features in a paid version not detailed in the repository.
- **Requirements:** 
- **Adopt for:** kereva-scanner is a specialized code scanner that assesses AI prompts and interactions with language models for potential security vulnerabilities and performance inefficiencies.

## Choose when

### Choose vigil-llm if…

- Tags unique to vigil-llm: adversarial-attacks, large-language-models.
- vigil-llm ships Docker support for self-hosted deployment.
- When deploying large language models that require high levels of input security, vigil-llm can be employed to detect maliciously crafted inputs intended to manipulate model behavior.

### Choose kereva-scanner if…

- Pricing: The tool is free under the Apache-2.0 license but may have features in a paid version not detailed in the repository..
- Requirements: .
- Tags unique to kereva-scanner: ai-code-review, hallucination, llm-evaluation, owasp-llm-top-10.
- Also covers Developer Tools.
- When you are developing applications involving AI-generated content or integrations with large language models, to ensure your prompts are secure against attacks such as prompt injection.

## When NOT to use vigil-llm

- If your application does not require high security against malicious inputs or if the risks of prompt injection are minimal due to controlled input sources, vigil-llm might be unnecessary.
- For projects that focus on optimizing output speed rather than input robustness, other tools might be more appropriate as vigil-llm could add significant processing overhead.

## When NOT to use kereva-scanner

- When your project does not involve interactions with language models or AI-generated content, since the scanner's utility is primarily in evaluating AI-related issues.
- If you are looking for a comprehensive general code linter that checks for coding standard violations or general best practices unrelated to security and performance of LLMs.

## Common questions

### What is the difference between vigil-llm and kereva-scanner?

vigil-llm: Detect prompt injections and other risky inputs in LLMs. kereva-scanner: Code scanner to check for issues in prompts and LLM calls. See the comparison table for live GitHub stats and shared categories.

### When should I choose vigil-llm over kereva-scanner?

Choose vigil-llm over kereva-scanner when Tags unique to vigil-llm: adversarial-attacks, large-language-models; vigil-llm ships Docker support for self-hosted deployment; When deploying large language models that require high levels of input security, vigil-llm can be employed to detect maliciously crafted inputs intended to manipulate model behavior.

### When should I choose kereva-scanner over vigil-llm?

Choose kereva-scanner over vigil-llm when Pricing: The tool is free under the Apache-2.0 license but may have features in a paid version not detailed in the repository.; Requirements: ; Tags unique to kereva-scanner: ai-code-review, hallucination, llm-evaluation, owasp-llm-top-10; Also covers Developer Tools; When you are developing applications involving AI-generated content or integrations with large language models, to ensure your prompts are secure against attacks such as prompt injection.

### When should I avoid vigil-llm?

If your application does not require high security against malicious inputs or if the risks of prompt injection are minimal due to controlled input sources, vigil-llm might be unnecessary. For projects that focus on optimizing output speed rather than input robustness, other tools might be more appropriate as vigil-llm could add significant processing overhead.

### When should I avoid kereva-scanner?

When your project does not involve interactions with language models or AI-generated content, since the scanner's utility is primarily in evaluating AI-related issues. If you are looking for a comprehensive general code linter that checks for coding standard violations or general best practices unrelated to security and performance of LLMs.

### Is vigil-llm or kereva-scanner more popular on GitHub?

vigil-llm has more GitHub stars (496 vs 78). Stars measure visibility, not whether either tool fits your constraints.

### Are vigil-llm and kereva-scanner open source?

Yes - both are open-source projects on GitHub (vigil-llm: Apache-2.0, kereva-scanner: Apache-2.0).

### Where can I find alternatives to vigil-llm or kereva-scanner?

GraphCanon lists graph-backed alternatives at [vigil-llm alternatives](/tools/deadbits-vigil-llm/alternatives) and [kereva-scanner alternatives](/tools/kereva-dev-kereva-scanner/alternatives) ([vigil-llm markdown twin](/tools/deadbits-vigil-llm/alternatives.md), [kereva-scanner markdown twin](/tools/kereva-dev-kereva-scanner/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/deadbits-vigil-llm-vs-kereva-dev-kereva-scanner.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.

### Which is better maintained, vigil-llm or kereva-scanner?

vigil-llm: Dormant. kereva-scanner: Dormant. 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 vigil-llm and kereva-scanner?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [vigil-llm trust report](/tools/deadbits-vigil-llm/trust); [kereva-scanner trust report](/tools/kereva-dev-kereva-scanner/trust).

---

**Machine-readable endpoints**

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