InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

149 results with any of your words Clear search and filters
  1. harmful_behaviors

    Datasets & benchmarks

    Hugging Face dataset by mlabonne

    Stale Hugging Face Hub, mlabonne 167 ♥Updated 2 years ago

    mlabonne/harmful_behaviors
  2. JBB-Behaviors

    Datasets & benchmarks

    Hugging Face dataset by JailbreakBench

    Stale Hugging Face Hub, JailbreakBench 139 ♥mitUpdated 2 years ago

    JailbreakBench/JBB-Behaviors
  3. superagent

    AI repositories

    Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

    Stale GitHub, superagent-ai 6,763 ★MITUpdated 2 months ago

    git clone https://github.com/superagent-ai/superagent.git
  4. humane-proxy

    MCP servers

    AI safety middleware — detects self-harm and criminal intent in LLM prompts.

    Stale Official MCP Registry, io.github.Vishisht16 Updated 4 months ago 2 notes

    humane-proxy@0.6.0
  5. Hugging Face dataset by strova-ai

    Indexed Hugging Face Hub, strova-ai 517 ♥apache-2.0Updated 14 months ago

    strova-ai/developer-productivity-simulated-behavioral-data
  6. Responsible 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.

    Stale GitHub, IBM 50 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/IBM/responsible-prompting-api.git
  7. NitroGen

    Models

    reinforcement learning model by nvidia

    Stale Hugging Face Hub, nvidia 577 ♥otherUpdated 9 months ago

    nvidia/NitroGen
  8. Product-design, conversion & behavioral-science principles for SaaS

    Stale GitHub, heliocosta-dev 901 ★Custom licence (see repository)Updated 2 months ago

    git clone https://github.com/heliocosta-dev/revenue-centric-design.git
  9. crab

    MCP servers

    CRAB (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.

    Indexed GitHub, lemonadesaltbagel 327 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/lemonadesaltbagel/crab.git
  10. rea

    Skills

    Reverse engineer anything with agents, from app behavior down to native binaries.

    Indexed GitHub, morluto 462.5k ★MITUpdated today

    git clone https://github.com/morluto/rea.git
  11. agentos

    Agents & frameworks

    TypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs

    Indexed GitHub, framerslab 689 ★Apache-2.0Updated today

    git clone https://github.com/framerslab/agentos.git
  12. ai-village

    Datasets & benchmarks

    Hugging Face dataset by aidigestorg

    Stale Hugging Face Hub, aidigestorg 138 ♥otherUpdated 40 days ago 1 note

    aidigestorg/ai-village
  13. 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。

    Stale GitHub, KarmenLoop 21 ★Apache-2.0Updated 23 days ago

    git clone https://github.com/KarmenLoop/user-behavior-personalization.git
  14. CoBRA

    Agents & frameworks

    [🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via classic social science experiments

    Stale GitHub, AISmithLab 97 ★MITUpdated 6 months ago

    git clone https://github.com/AISmithLab/CoBRA.git
  15. Behavior Trees

    MCP servers

    Validate, convert (behavior3 JSON, BehaviorTree.CPP XML) and open behavior trees in a visual editor

    Stale Official MCP Registry, io.github.behaviortrees Updated 2 days ago 2 notes

    behaviortrees@0.2.0
  16. MagicDance

    AI repositories

    [ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

    Stale GitHub, Boese0601 778 ★Custom licence (see repository)Updated 2 years ago

    git clone https://github.com/Boese0601/MagicDance.git
  17. skillcheck

    Prompts

    Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.

    Stale GitHub, sx4im 30 ★MITUpdated 13 days ago

    git clone https://github.com/sx4im/skillcheck.git
  18. HTTP API for triggering instances of custom behavioral events

    Indexed APIs.guru OpenAPI Directory, hubapi.com Updated 4 years ago

  19. Behavioral health statistics from SAMHSA surveys including NSDUH

    Stale Official MCP Registry, com.olyport Updated 7 months ago 1 note

  20. Premium agentic endpoint for botnet-behavior-analyzer-mcp.

    Stale Official MCP Registry, io.github.Evozim Updated 3 months ago 1 note

  21. Behavioral science tools for commerce — personas, nudges, preferences, friction audits.

    Stale Official MCP Registry, io.phoslabs Updated 41 days ago 2 notes

  22. Infographic

    Prompts

    Generate 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

    Indexed prompts.chat (CC0 prompt collection), ionicdebut@gmail.com CC0-1.0

  23. Behavior Runtime MCP

    MCP servers

    In-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.

    Stale Official MCP Registry, io.github.putervision Updated 44 days ago 1 note

    @putervision/behavior-mcp@0.4.1
  24. Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.

    Stale Official MCP Registry, dev.gtfo Updated 4 months ago 1 note

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.