Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
cyber-security
Datasets & benchmarksHugging Face dataset by Vyber07
Vyber07/cyber-security -
Ultimate-Offensive-Red-Team
Datasets & benchmarksHugging Face dataset by WNT3D
WNT3D/Ultimate-Offensive-Red-Team -
OmniAction
Datasets & benchmarksHugging Face dataset by OpenMOSS-Team
OpenMOSS-Team/OmniAction -
ToolACE
Datasets & benchmarksHugging Face dataset by Team-ACE
Team-ACE/ToolACE -
AM-DeepSeek-R1-Distilled-1.4M
Datasets & benchmarksHugging Face dataset by a-m-team
a-m-team/AM-DeepSeek-R1-Distilled-1.4M -
multi-agents
Datasets & benchmarksMulti-agent teams for real work: run teams of coding agents (Claude Code, Codex, any model) in isolated git worktrees, and measure whether the team beats a solo agent on cost and results.
git clone https://github.com/BichengWang/multi-agents.git -
wildjailbreak
Datasets & benchmarksHugging Face dataset by allenai
allenai/wildjailbreak -
AICGSecEval
Datasets & benchmarksA.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.
git clone https://github.com/Tencent/AICGSecEval.git -
autoguardrails
Datasets & benchmarksAlignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
git clone https://github.com/SantanderAI/autoguardrails.git -
xorcise
Datasets & benchmarksRun cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.
git clone https://github.com/xorcise-ai/xorcise.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
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.