Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
PyRIT
AI repositoriesOpen-source AI red teaming toolkit from Microsoft. Test generative AI systems with automated scans, adaptive multi-turn attacks, and a web UI.
git clone https://github.com/microsoft/PyRIT.git -
agentic_security
Agents & frameworksAgentic LLM Vulnerability Scanner / AI red teaming kit 🧪
git clone https://github.com/msoedov/agentic_security.git -
AI-Infra-Guard
AI repositoriesA full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
git clone https://github.com/Tencent/AI-Infra-Guard.git -
nuguard
MCP serversAI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
git clone https://github.com/NuGuardAI/nuguard.git -
Qwen3.8-27B-Uncensored-FP8
Modelsimage text to text model by orcarouter · transformers
orcarouter/Qwen3.8-27B-Uncensored-FP8 -
Qwen3.8-27B-Uncensored-GGUF
Modelsimage text to text model by orcarouter · gguf
orcarouter/Qwen3.8-27B-Uncensored-GGUF -
giskard-oss
AI repositories🐢 Open-Source Evaluation & Testing library for LLM Agents
git clone https://github.com/Giskard-AI/giskard-oss.git -
image text to text model by orcarouter · gguf
orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF -
Qwen3.8-27B-Uncensored-MLX
Modelsimage text to text model by orcarouter · mlx
orcarouter/Qwen3.8-27B-Uncensored-MLX -
agentic-radar
AI repositoriesA security scanner for your LLM agentic workflows
git clone https://github.com/splx-ai/agentic-radar.git -
Qwen3.8-27B-Uncensored
Modelsimage text to text model by orcarouter · transformers
orcarouter/Qwen3.8-27B-Uncensored -
Qwen3.8-27B-Uncensored-NVFP4
Modelsimage text to text model by orcarouter · transformers
orcarouter/Qwen3.8-27B-Uncensored-NVFP4 -
text generation model by orcarouter · gguf
orcarouter/DeepSeek-V4.1-Flash-1017-abliterated-GGUF -
agent-opfor
MCP serversOpen-source adversary emulation for AI agents and MCP servers.
git clone https://github.com/KeyValueSoftwareSystems/agent-opfor.git -
LFM3-1.7B-abliterated
Modelstext generation model by orcarouter · transformers
orcarouter/LFM3-1.7B-abliterated -
text generation model by orcarouter · gguf
orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF -
guardana
MCP serversOpen-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
git clone https://github.com/guardana/guardana.git -
jailbreak-archives
PromptsA structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.
git clone https://github.com/e2sy/jailbreak-archives.git -
AIRTBench-Code
Datasets & benchmarksCode Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
git clone https://github.com/dreadnode/AIRTBench-Code.git -
ai-security-research-radar
SkillsAI Security Research Radar — AI for security and security for AI
git clone https://github.com/Neetx/ai-security-research-radar.git -
Argus
Agents & frameworksOpen-source red-team testing for AI agents. 266 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock payments. CLI, SARIF, GitHub Action.
git clone https://github.com/gy15901580825/Argus.git -
Heisto
MCP serversPrompt-injection Guard checks and public AI red-teaming arena data from Heisto on Solana.
-
promptfoo-action
PromptsThe GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
git clone https://github.com/promptfoo/promptfoo-action.git -
hermes-jailbench
SkillsZero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench
git clone https://github.com/hermes-labs-ai/hermes-jailbench.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.