Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
harmful_behaviors
Datasets & benchmarksHugging Face dataset by mlabonne
mlabonne/harmful_behaviors -
JBB-Behaviors
Datasets & benchmarksHugging Face dataset by JailbreakBench
JailbreakBench/JBB-Behaviors -
superagent
AI repositoriesSuperagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
git clone https://github.com/superagent-ai/superagent.git -
humane-proxy
MCP serversAI safety middleware — detects self-harm and criminal intent in LLM prompts.
humane-proxy@0.6.0 -
developer-productivity-simulated-behavioral-data
Datasets & benchmarksHugging Face dataset by strova-ai
strova-ai/developer-productivity-simulated-behavioral-data -
responsible-prompting-api
PromptsResponsible Prompting is an LLM-agnostic tool that aims at dynamically supporting users in crafting prompts that embed responsible intentions and help avoid harmful, adversarial prompts.
git clone https://github.com/IBM/responsible-prompting-api.git -
NitroGen
Modelsreinforcement learning model by nvidia
nvidia/NitroGen -
revenue-centric-design
SkillsProduct-design, conversion & behavioral-science principles for SaaS
git clone https://github.com/heliocosta-dev/revenue-centric-design.git -
crab
MCP serversCRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
git clone https://github.com/lemonadesaltbagel/crab.git -
rea
SkillsReverse engineer anything with agents, from app behavior down to native binaries.
git clone https://github.com/morluto/rea.git -
agentos
Agents & frameworksTypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs
git clone https://github.com/framerslab/agentos.git -
ai-village
Datasets & benchmarksHugging Face dataset by aidigestorg
aidigestorg/ai-village -
Local user preferences with sourced corrections, scoped recall, and Codex/Cursor host adapters. / 本地保存带来源的偏好,支持更正、限定检索与 Codex/Cursor 适配。
git clone https://github.com/KarmenLoop/user-behavior-personalization.git -
CoBRA
Agents & frameworks[🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via classic social science experiments
git clone https://github.com/AISmithLab/CoBRA.git -
Behavior Trees
MCP serversValidate, convert (behavior3 JSON, BehaviorTree.CPP XML) and open behavior trees in a visual editor
behaviortrees@0.2.0 -
MagicDance
AI repositories[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
git clone https://github.com/Boese0601/MagicDance.git -
skillcheck
PromptsBlind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.
git clone https://github.com/sx4im/skillcheck.git -
Custom Behavioral Events API
Public APIsHTTP API for triggering instances of custom behavioral events
-
SAMHSA Behavioral Health
MCP serversBehavioral health statistics from SAMHSA surveys including NSDUH
-
Execute botnet-behavior-analyzer-mcp
MCP serversPremium agentic endpoint for botnet-behavior-analyzer-mcp.
-
Phos Labs Behavioral Science
MCP serversBehavioral science tools for commerce — personas, nudges, preferences, friction audits.
-
Infographic
PromptsGenerate info graphics that depict story of how an given event with the context of that event can have impact on multiple zones, harm on the direct system it belongs to etc
-
Behavior Runtime MCP
MCP serversIn-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.
@putervision/behavior-mcp@0.4.1 -
Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.
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.