From e6d6a23d8a93b09828aacbac2da4f6a80479057a Mon Sep 17 00:00:00 2001 From: Leon Derczynski Date: Wed, 19 Nov 2025 12:57:06 +0100 Subject: [PATCH 1/7] add list of projects using/supporting garak --- PROJECTS.md | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 PROJECTS.md diff --git a/PROJECTS.md b/PROJECTS.md new file mode 100644 index 000000000..03a0dd81e --- /dev/null +++ b/PROJECTS.md @@ -0,0 +1,20 @@ +# Projects and products consuming, wrapping, and using garak + +## Integrations + +* [Tumeryk](http://www.tumeryk.com) - The Tumeryk platform empowers organizations to safeguard AI systems, ensuring secure, reliable, and policy-aligned deployments. Scan LLMs & endpoints to prevent jailbreaks, data leaks, and IP exposure. +* [Vijil](https://www.vijil.ai/) - Vijil helps organizations build and operate autonomous agents that humans can trust. Garak forms part of their “vijil score”. They have an API and efficient orchestration engine. +* [Deepchecks](https://deepchecks.com) - Integrating garak and guardrails together: https://deepchecks.com/the-best-llm-safety-net-to-date-deepchecks-garak-and-nemo-guardrails-all-in-one-bundle/ . Example use of garak tools: https://llmdocs.deepchecks.com/docs/pentesting-your-llm-pipeline +* [Mindgard](https://www.mindgard.ai) - An AI security platform, Mindgard integrate garak as part of their pentesting & eval suite +* [Giskard](https://giskard.ai) - Giskard integration - https://docs.giskard.ai/en/stable/reference/scan/llm_detectors.html +* OpsMX +* Upwind + +## Tooling + +* [Garak Studio](https://github.com/hasbegun/garak_studio) - OSS GUI for garak + + +## Want to be added? + +Want a project mentioned, or the description d? Send a pull request with details. We can't take an opinion on how good any of these are, so please use a neutral tone. \ No newline at end of file From 336cc4874f5afbed07d93a7f4a88f77f85a8bded Mon Sep 17 00:00:00 2001 From: Leon Derczynski Date: Wed, 19 Nov 2025 12:58:03 +0100 Subject: [PATCH 2/7] put OSS at top --- PROJECTS.md | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/PROJECTS.md b/PROJECTS.md index 03a0dd81e..9a0dad5d1 100644 --- a/PROJECTS.md +++ b/PROJECTS.md @@ -1,5 +1,12 @@ # Projects and products consuming, wrapping, and using garak +## Tooling + +(open-source / free only) + +* [Garak Studio](https://github.com/hasbegun/garak_studio) - OSS GUI for garak + + ## Integrations * [Tumeryk](http://www.tumeryk.com) - The Tumeryk platform empowers organizations to safeguard AI systems, ensuring secure, reliable, and policy-aligned deployments. Scan LLMs & endpoints to prevent jailbreaks, data leaks, and IP exposure. @@ -10,11 +17,8 @@ * OpsMX * Upwind -## Tooling - -* [Garak Studio](https://github.com/hasbegun/garak_studio) - OSS GUI for garak ## Want to be added? -Want a project mentioned, or the description d? Send a pull request with details. We can't take an opinion on how good any of these are, so please use a neutral tone. \ No newline at end of file +Want a project mentioned, or the description d? Send a pull request with details. We can't take an opinion on how good any of these are, so please use a neutral tone. From 704088118e84783d3a303a6f1a8ecb3e32cb7407 Mon Sep 17 00:00:00 2001 From: Leon Derczynski Date: Thu, 20 Nov 2025 11:57:47 +0100 Subject: [PATCH 3/7] include licenses, update disclaimer & tone statement --- PROJECTS.md | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/PROJECTS.md b/PROJECTS.md index 9a0dad5d1..9978a2283 100644 --- a/PROJECTS.md +++ b/PROJECTS.md @@ -4,7 +4,9 @@ (open-source / free only) -* [Garak Studio](https://github.com/hasbegun/garak_studio) - OSS GUI for garak +* [TrustyAI Garak](https://github.com/trustyai-explainability/llama-stack-provider-trustyai-garak) (Apache) - Out-of-Tree Llama Stack Eval Provider for Garak Red Teaming +* [Garak-MCP](https://github.com/EdenYavin/Garak-MCP) (MIT license) - MCP Server for garak + ## Integrations @@ -21,4 +23,7 @@ ## Want to be added? -Want a project mentioned, or the description d? Send a pull request with details. We can't take an opinion on how good any of these are, so please use a neutral tone. +Want a project mentioned, or the description updated? Send a pull request with details. Please use a [neutral tone](https://en.wikipedia.org/wiki/Wikipedia:Neutral_point_of_view). + +Inclusion on this page does not imply an endorsement by the maintainers or NVIDIA. + From 13ceb0974062d80513cf97fd0fdaf9040717395f Mon Sep 17 00:00:00 2001 From: Leon Derczynski Date: Thu, 20 Nov 2025 12:03:11 +0100 Subject: [PATCH 4/7] flesh out integrator descriptions --- PROJECTS.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/PROJECTS.md b/PROJECTS.md index 9978a2283..5e984192d 100644 --- a/PROJECTS.md +++ b/PROJECTS.md @@ -16,8 +16,8 @@ * [Deepchecks](https://deepchecks.com) - Integrating garak and guardrails together: https://deepchecks.com/the-best-llm-safety-net-to-date-deepchecks-garak-and-nemo-guardrails-all-in-one-bundle/ . Example use of garak tools: https://llmdocs.deepchecks.com/docs/pentesting-your-llm-pipeline * [Mindgard](https://www.mindgard.ai) - An AI security platform, Mindgard integrate garak as part of their pentesting & eval suite * [Giskard](https://giskard.ai) - Giskard integration - https://docs.giskard.ai/en/stable/reference/scan/llm_detectors.html -* OpsMX -* Upwind +* [OpsMX](https://www.opsmx.com/) - "OpsMx Delivery Shield embeds Garak’s adversarial testing engine to continuously probe, monitor, and guard live AI and LLM workloads against jailbreaks, data leaks, and policy violations" - https://www.opsmx.com/dynamic-runtime-ai-security +* [Upwind](https://www.upwind.io/) - "Upwind secures your cloud deployments, configurations, and applications through a runtime fabric that provides real-time visibility from the inside out" From be6857625a029cbed85edea5420acded551aca67 Mon Sep 17 00:00:00 2001 From: Leon Derczynski Date: Fri, 21 Nov 2025 16:22:04 +0100 Subject: [PATCH 5/7] fix md link Co-authored-by: Erick Galinkin Signed-off-by: Leon Derczynski --- PROJECTS.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/PROJECTS.md b/PROJECTS.md index 5e984192d..b4767842d 100644 --- a/PROJECTS.md +++ b/PROJECTS.md @@ -15,7 +15,7 @@ * [Vijil](https://www.vijil.ai/) - Vijil helps organizations build and operate autonomous agents that humans can trust. Garak forms part of their “vijil score”. They have an API and efficient orchestration engine. * [Deepchecks](https://deepchecks.com) - Integrating garak and guardrails together: https://deepchecks.com/the-best-llm-safety-net-to-date-deepchecks-garak-and-nemo-guardrails-all-in-one-bundle/ . Example use of garak tools: https://llmdocs.deepchecks.com/docs/pentesting-your-llm-pipeline * [Mindgard](https://www.mindgard.ai) - An AI security platform, Mindgard integrate garak as part of their pentesting & eval suite -* [Giskard](https://giskard.ai) - Giskard integration - https://docs.giskard.ai/en/stable/reference/scan/llm_detectors.html +* [Giskard](https://giskard.ai) - [Giskard integration](https://docs.giskard.ai/en/stable/reference/scan/llm_detectors.html). * [OpsMX](https://www.opsmx.com/) - "OpsMx Delivery Shield embeds Garak’s adversarial testing engine to continuously probe, monitor, and guard live AI and LLM workloads against jailbreaks, data leaks, and policy violations" - https://www.opsmx.com/dynamic-runtime-ai-security * [Upwind](https://www.upwind.io/) - "Upwind secures your cloud deployments, configurations, and applications through a runtime fabric that provides real-time visibility from the inside out" From d056a4e9c2080565f4e055c5c76cb179d2fdc81b Mon Sep 17 00:00:00 2001 From: Leon Derczynski Date: Fri, 21 Nov 2025 16:22:26 +0100 Subject: [PATCH 6/7] Make descriptive text into link text Co-authored-by: Erick Galinkin Signed-off-by: Leon Derczynski --- PROJECTS.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/PROJECTS.md b/PROJECTS.md index b4767842d..b9efa1352 100644 --- a/PROJECTS.md +++ b/PROJECTS.md @@ -13,7 +13,7 @@ * [Tumeryk](http://www.tumeryk.com) - The Tumeryk platform empowers organizations to safeguard AI systems, ensuring secure, reliable, and policy-aligned deployments. Scan LLMs & endpoints to prevent jailbreaks, data leaks, and IP exposure. * [Vijil](https://www.vijil.ai/) - Vijil helps organizations build and operate autonomous agents that humans can trust. Garak forms part of their “vijil score”. They have an API and efficient orchestration engine. -* [Deepchecks](https://deepchecks.com) - Integrating garak and guardrails together: https://deepchecks.com/the-best-llm-safety-net-to-date-deepchecks-garak-and-nemo-guardrails-all-in-one-bundle/ . Example use of garak tools: https://llmdocs.deepchecks.com/docs/pentesting-your-llm-pipeline +* [Deepchecks](https://deepchecks.com) - [Integrating garak and NeMo Guardrails together](https://deepchecks.com/the-best-llm-safety-net-to-date-deepchecks-garak-and-nemo-guardrails-all-in-one-bundle/); [Example use of garak tools](https://llmdocs.deepchecks.com/docs/pentesting-your-llm-pipeline) * [Mindgard](https://www.mindgard.ai) - An AI security platform, Mindgard integrate garak as part of their pentesting & eval suite * [Giskard](https://giskard.ai) - [Giskard integration](https://docs.giskard.ai/en/stable/reference/scan/llm_detectors.html). * [OpsMX](https://www.opsmx.com/) - "OpsMx Delivery Shield embeds Garak’s adversarial testing engine to continuously probe, monitor, and guard live AI and LLM workloads against jailbreaks, data leaks, and policy violations" - https://www.opsmx.com/dynamic-runtime-ai-security From 36f4db034ecafb8b6f8446337933e6bc29a55381 Mon Sep 17 00:00:00 2001 From: Leon Derczynski Date: Tue, 25 Nov 2025 14:42:59 +0100 Subject: [PATCH 7/7] move to table, add garak report repo --- PROJECTS.md | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) diff --git a/PROJECTS.md b/PROJECTS.md index b9efa1352..1d2e4749d 100644 --- a/PROJECTS.md +++ b/PROJECTS.md @@ -4,25 +4,32 @@ (open-source / free only) -* [TrustyAI Garak](https://github.com/trustyai-explainability/llama-stack-provider-trustyai-garak) (Apache) - Out-of-Tree Llama Stack Eval Provider for Garak Red Teaming -* [Garak-MCP](https://github.com/EdenYavin/Garak-MCP) (MIT license) - MCP Server for garak + + +| Name | Licence | Description | +| - | - | - | +| [TrustyAI Garak](https://github.com/trustyai-explainability/llama-stack-provider-trustyai-garak) | Apache | Out-of-Tree Llama Stack Eval Provider for Garak Red Teaming | +| [Garak-MCP](https://github.com/EdenYavin/Garak-MCP) | MIT license | MCP Server for garak | +| [Garak Report](https://github.com/lreading/garak-repo) | Apache-2.0 | A repository for your Garak runs, as well as a modern visualizer. | + ## Integrations -* [Tumeryk](http://www.tumeryk.com) - The Tumeryk platform empowers organizations to safeguard AI systems, ensuring secure, reliable, and policy-aligned deployments. Scan LLMs & endpoints to prevent jailbreaks, data leaks, and IP exposure. -* [Vijil](https://www.vijil.ai/) - Vijil helps organizations build and operate autonomous agents that humans can trust. Garak forms part of their “vijil score”. They have an API and efficient orchestration engine. -* [Deepchecks](https://deepchecks.com) - [Integrating garak and NeMo Guardrails together](https://deepchecks.com/the-best-llm-safety-net-to-date-deepchecks-garak-and-nemo-guardrails-all-in-one-bundle/); [Example use of garak tools](https://llmdocs.deepchecks.com/docs/pentesting-your-llm-pipeline) -* [Mindgard](https://www.mindgard.ai) - An AI security platform, Mindgard integrate garak as part of their pentesting & eval suite -* [Giskard](https://giskard.ai) - [Giskard integration](https://docs.giskard.ai/en/stable/reference/scan/llm_detectors.html). -* [OpsMX](https://www.opsmx.com/) - "OpsMx Delivery Shield embeds Garak’s adversarial testing engine to continuously probe, monitor, and guard live AI and LLM workloads against jailbreaks, data leaks, and policy violations" - https://www.opsmx.com/dynamic-runtime-ai-security -* [Upwind](https://www.upwind.io/) - "Upwind secures your cloud deployments, configurations, and applications through a runtime fabric that provides real-time visibility from the inside out" +| Name | Description | +| - | - | +| [Tumeryk](http://www.tumeryk.com) | The Tumeryk platform empowers organizations to safeguard AI systems, ensuring secure, reliable, and policy-aligned deployments. Scan LLMs & endpoints to prevent jailbreaks, data leaks, and IP exposure | +| [Vijil](https://www.vijil.ai/) | Vijil helps organizations build and operate autonomous agents that humans can trust. Garak forms part of their “vijil score”. They have an API and efficient orchestration engine | +| [Deepchecks](https://deepchecks.com) | [Integrating garak and NeMo Guardrails together](https://deepchecks.com/the-best-llm-safety-net-to-date-deepchecks-garak-and-nemo-guardrails-all-in-one-bundle/); [Example use of garak tools](https://llmdocs.deepchecks.com/docs/pentesting-your-llm-pipeline) | +| [Mindgard](https://www.mindgard.ai) | An AI security platform, Mindgard integrate garak as part of their pentesting & eval suite | +| [Giskard](https://giskard.ai) | [Giskard integration](https://docs.giskard.ai/en/stable/reference/scan/llm_detectors.html) | +| [OpsMX](https://www.opsmx.com/) | "OpsMx Delivery Shield embeds Garak’s adversarial testing engine to continuously probe, monitor, and guard live AI and LLM workloads against jailbreaks, data leaks, and policy violations" https://www.opsmx.com/dynamic-runtime-ai-security | +| [Upwind](https://www.upwind.io/) | "Upwind secures your cloud deployments, configurations, and applications through a runtime fabric that provides real-time visibility from the inside out" | ## Want to be added? - Want a project mentioned, or the description updated? Send a pull request with details. Please use a [neutral tone](https://en.wikipedia.org/wiki/Wikipedia:Neutral_point_of_view). Inclusion on this page does not imply an endorsement by the maintainers or NVIDIA.