--- title: "vigil-llm vs rebuff" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/deadbits-vigil-llm-vs-protectai-rebuff" tools: ["deadbits-vigil-llm", "protectai-rebuff"] --- # vigil-llm vs rebuff *GraphCanon updated Jul 12, 2026* ## Verdict Pick vigil-llm when vigil-llm is primarily Python; rebuff is TypeScript; pick rebuff when rebuff is primarily TypeScript; vigil-llm is Python. [vigil-llm](https://vigil.deadbits.ai/) reports 489 GitHub stars, 55 forks, and 16 open issues, last pushed Jan 31, 2024. [rebuff](https://playground.rebuff.ai) has 1.5k stars, 137 forks, and 33 open issues, last pushed Aug 7, 2024. Figures are from public GitHub metadata via [vigil-llm's repository](https://github.com/deadbits/vigil-llm) and [rebuff's repository](https://github.com/protectai/rebuff). | | [vigil-llm](/tools/deadbits-vigil-llm.md) | [rebuff](/tools/protectai-rebuff.md) | | --- | --- | --- | | Tagline | ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs | LLM Prompt Injection Detector | | Stars | 489 | 1,511 | | Forks | 55 | 137 | | Open issues | 16 | 33 | | Language | Python | TypeScript | | Adopt for | Vigil-LLM is specifically designed for detecting prompt injections and jailbreaks in LLM inputs, offering unique capabilities not found in all security tools. | - | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | Evaluation & Observability, LLM Frameworks, Vector Databases | Evaluation & Observability, LLM Frameworks, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [vigil-llm](/tools/deadbits-vigil-llm.md) | [rebuff](/tools/protectai-rebuff.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Archived (8%) | | Days since push | 891d | 703d | | Archived on GitHub | No | Yes | | Open issues (now) | 16 | 33 | | Owner type | User | Organization | | Full report | [trust report](/tools/deadbits-vigil-llm/trust.md) | [trust report](/tools/protectai-rebuff/trust.md) | ## Decision facts: vigil-llm - **Pricing:** freemium - Vigil-LLM is open-source under the Apache License 2.0 and freely available to download. However, additional support or services may be offered on a paid basis depending on the context of usage. - **Requirements:** Min 4 GB RAM - **Adopt for:** Vigil-LLM is specifically designed for detecting prompt injections and jailbreaks in LLM inputs, offering unique capabilities not found in all security tools. ## Choose when ### Choose vigil-llm if… - vigil-llm is primarily Python; rebuff is TypeScript. - Pricing: Vigil-LLM is open-source under the Apache License 2.0 and freely available to download. However, additional support or services may be offered on a paid basis depending on the context of usage.. - Requirements: Min 4 GB RAM. - Tags unique to vigil-llm: adversarial-attacks, adversarial-machine-learning, large-language-models, llm-security. - When integrating large language models into applications that need robust protection against prompt injection attacks. ### Choose rebuff if… - rebuff is primarily TypeScript; vigil-llm is Python. - Tags unique to rebuff: llm, prompt-engineering, prompts, security. - More GitHub stars (1.5k vs 489) - visibility, not fit. ## When NOT to use vigil-llm - If the focus of security efforts is solely on data breaches and not specifically on securing against adversarial machine learning techniques like prompt injections or jailbreaks. - When your environment is set up without Python or YARA v4.3.2, as these are prerequisites for using Vigil-LLM effectively. ## When NOT to use rebuff - rebuff is archived on GitHub. Prefer an active alternative unless you maintain a private fork or need a frozen dependency. - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## Common questions ### What is the difference between vigil-llm and rebuff? vigil-llm: ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs. rebuff: LLM Prompt Injection Detector. See the comparison table for live GitHub stats and shared categories. ### When should I choose vigil-llm over rebuff? Choose vigil-llm over rebuff when vigil-llm is primarily Python; rebuff is TypeScript; Pricing: Vigil-LLM is open-source under the Apache License 2.0 and freely available to download. However, additional support or services may be offered on a paid basis depending on the context of usage.; Requirements: Min 4 GB RAM; Tags unique to vigil-llm: adversarial-attacks, adversarial-machine-learning, large-language-models, llm-security; When integrating large language models into applications that need robust protection against prompt injection attacks. ### When should I choose rebuff over vigil-llm? Choose rebuff over vigil-llm when rebuff is primarily TypeScript; vigil-llm is Python; Tags unique to rebuff: llm, prompt-engineering, prompts, security; More GitHub stars (1.5k vs 489) - visibility, not fit. ### When should I avoid vigil-llm? If the focus of security efforts is solely on data breaches and not specifically on securing against adversarial machine learning techniques like prompt injections or jailbreaks. When your environment is set up without Python or YARA v4.3.2, as these are prerequisites for using Vigil-LLM effectively. ### When should I avoid rebuff? rebuff is archived on GitHub. Prefer an active alternative unless you maintain a private fork or need a frozen dependency. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### Is vigil-llm or rebuff more popular on GitHub? rebuff has more GitHub stars (1,511 vs 489). Stars measure visibility, not whether either tool fits your constraints. ### Are vigil-llm and rebuff open source? Yes - both are open-source projects on GitHub (vigil-llm: Apache-2.0, rebuff: Apache-2.0). ### Where can I find alternatives to vigil-llm or rebuff? GraphCanon lists graph-backed alternatives at [vigil-llm alternatives](/tools/deadbits-vigil-llm/alternatives) and [rebuff alternatives](/tools/protectai-rebuff/alternatives) ([vigil-llm markdown twin](/tools/deadbits-vigil-llm/alternatives.md), [rebuff markdown twin](/tools/protectai-rebuff/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-protectai-rebuff.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, vigil-llm or rebuff? vigil-llm: Dormant. rebuff: Archived. 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 rebuff? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [vigil-llm trust report](/tools/deadbits-vigil-llm/trust); [rebuff trust report](/tools/protectai-rebuff/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/_