# Llama Guard vs Rebuff

| Attribute | Llama Guard | Rebuff |
|---|---|---|
| **vioscaleAI score** | 43.9 (25% (low)) | 36.5 (24% (low)) |
| activity.commits_last_30d | 3 | 0 |
| adoption.dependent_repos | 0 | 1 |
| adoption.github_stars | 4,431 | 1,529 |
| content.faq | `[{"answer":"A suite of input/output moderation models and security evaluation benchmarks designed to help developers build safer generative AI applications. Includes tools to detect prompt injection, jailbreaking attempts, and other violating content. It is indexed under AI Guardrails.","source":"https://github.com/pricing","question":"What is Llama Guard?","confidence":0.6},{"answer":"Llama Guard is open source, so it can be self-hosted and used at no licence cost. Pricing changes often, so verify at source before relying on it.","source":"https://github.com/pricing","question":"Is Llama Guard free to use?","confidence":0.6},{"answer":"Llama Guard supports a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://github.com/pricing","question":"What platforms does Llama Guard support?","confidence":0.6},{"answer":"Yes. Llama Guard can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://github.com/pricing","question":"Can Llama Guard be self-hosted?","confidence":0.6}]` | `[{"answer":"A framework that protects AI systems from prompt injection attacks through four defense mechanisms: input heuristics, LLM-based analysis, vector database pattern recognition, and canary token detection. Currently in alpha/prototype stage. It is indexed under AI Guardrails.","source":"https://github.com/pricing","question":"What is Rebuff?","confidence":0.6},{"answer":"Rebuff offers a free tier, so you can start without paying. Pricing changes often, so verify at source before relying on it.","source":"https://github.com/pricing","question":"Is Rebuff free?","confidence":0.6},{"answer":"Rebuff supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://github.com/pricing","question":"What platforms does Rebuff support?","confidence":0.6},{"answer":"We have only confirmed a cloud / SaaS deployment for Rebuff, so it appears to be vendor-hosted. If a self-hosted option exists we have not found it documented publicly.","source":"https://github.com/pricing","question":"Can Rebuff be self-hosted?","confidence":0.6},{"answer":"We have confirmed 3 integrations for Rebuff, including OpenAI, Supabase and Pinecone. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://github.com/pricing","question":"What does Rebuff integrate with?","confidence":0.6},{"answer":"Yes. Rebuff is published under the Apache-2.0 licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.","source":"https://github.com/protectai/rebuff","question":"Is Rebuff open source?","confidence":0.95},{"answer":"Rebuff is available worldwide. Its primary market is the United States.","source":"https://github.com/pricing","question":"Where is Rebuff available?","confidence":0.5}]` |
| deployment.options | `{"self_hosted":true}` | `{"self_hosted":true}` |
| description.long | Open-source moderation models that detect and help prevent harmful content in AI language model inputs and outputs, with capabilities including prompt injection and jailbreak attack detection. | A framework that protects AI systems from prompt injection attacks through four defense mechanisms: input heuristics, LLM-based analysis, vector database pattern recognition, and canary token detection. Currently in alpha/prototype stage. |
| features.capabilities | `{"iso_27001":false,"soc2_type_ii":false,"pricing_model":"free_open_source","architecture_model":"open_source_python_library","rag_retrieval_chunk_poisoning_defense":false,"prompt_injection_and_jailbreak_blocking":true,"inbound_pii_and_credit_card_masking_redaction":false,"streaming_token_interception_and_chunked_eval":false,"sub_50ms_latency_guarantees_for_proxy_routing":false,"custom_regex_and_deterministic_denylist_rulesets":false,"outbound_toxicity_and_competitor_mention_blocking":true,"zero_data_retention_and_prompt_privacy_guarantees":true,"hallucination_and_topical_off_brand_drift_detection":false}` | `{"architecture_model":"managed_cloud_inline_proxy","prompt_injection_and_jailbreak_blocking":true,"custom_regex_and_deterministic_denylist_rulesets":true,"zero_data_retention_and_prompt_privacy_guarantees":false}` |
| integrations.count | - | 3 |
| integrations.list | - | `[{"name":"OpenAI"},{"name":"Supabase"},{"name":"Pinecone"}]` |
| language.primary | Python | TypeScript |
| license.spdx | - | Apache-2.0 |
| market.availability | - | `{"primaryMarkets":["US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true}` | `{"cli":true,"web":true}` |
| pricing | `{"type":"open_source","summary":"Free and open source under MIT license","freeTier":true,"sourceUrl":"https://github.com/pricing","retrievedAt":"2026-08-21T10:59:49.492Z"}` | `{"type":"open_source","freeTier":true,"sourceUrl":"https://github.com/pricing","retrievedAt":"2026-09-14T09:22:59.302Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | open_source | commercial |
| pricing.price_level | free | free |
| pricing.transparent | yes | no |
| release.history | - | `[{"url":"https://github.com/protectai/rebuff/releases/tag/v0.1.1","date":"2024-01-20T01:11:48Z","type":"stable","version":"v0.1.1"},{"url":"https://github.com/protectai/rebuff/releases/tag/v0.1.0","date":"2024-01-20T01:03:53Z","type":"stable","version":"v0.1.0"},{"url":"https://github.com/protectai/rebuff/releases/tag/v0.0.6","date":"2024-01-20T00:48:23Z","type":"stable","version":"v0.0.6"}]` |
| security.scorecard | 5.9 | - |
| security.trust_center | https://github.com/security | https://github.com/security |
| security.vulnerabilities | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=codeshield&per_page=100","last_12m":0,"max_severity":null}` | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=rebuff&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (AI Guardrails)

| Capability | Llama Guard | Rebuff |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Architecture model | Open source python library | Managed cloud inline proxy |
| Prompt injection and jailbreak blocking | ✓ | ✓ |
| Inbound pii and credit card masking redaction | ✗ | - |
| Outbound toxicity and competitor mention blocking | ✓ | - |
| Hallucination and topical off brand drift detection | ✗ | - |
| Sub 50ms latency guarantees for proxy routing | ✗ | - |
| Custom regex and deterministic denylist rulesets | ✗ | ✓ |
| Streaming token interception and chunked eval | ✗ | - |
| Rag retrieval chunk poisoning defense | ✗ | - |
| Zero data retention and prompt privacy guarantees | ✓ | ✗ |
| SOC2 type ii | ✗ | - |
| ISO 27001 | ✗ | - |
| Pricing model | Free open source | - |

*Source: vioscaleAI. Generated 2026-10-16T18:31:57.217Z. "-" = undocumented, not absent.*