InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Safety-Prompts

    Prompts

    Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。

    Stale GitHub, thu-coai 1,223 ★Apache-2.0Updated 2 years ago

    git clone https://github.com/thu-coai/Safety-Prompts.git
  2. Guardrails

    AI repositories

    NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

    Indexed GitHub, NVIDIA-NeMo 7,505 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/NVIDIA-NeMo/Guardrails.git
  3. PyRIT

    AI repositories

    Open-source AI red teaming toolkit from Microsoft. Test generative AI systems with automated scans, adaptive multi-turn attacks, and a web UI.

    Indexed GitHub, microsoft 4,869 ★MITUpdated today

    git clone https://github.com/microsoft/PyRIT.git
  4. UGI-Leaderboard

    Tools & apps

    Hugging Face space by DontPlanToEnd

    Indexed Hugging Face Hub, DontPlanToEnd 2,216 ♥Updated 30 days ago 1 note

    DontPlanToEnd/UGI-Leaderboard
  5. AISafetyHot

    MCP servers

    AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.

    Indexed GitHub, wuyoscar 2,127 ★Custom licence (see repository)Updated today

    git clone https://github.com/wuyoscar/AISafetyHot.git
  6. awesome-ai-safety

    Docs & tutorials

    📚 A curated list of papers & technical articles on AI Quality & Safety

    Stale GitHub, Giskard-AI 226 ★Apache-2.0Updated 19 months ago

    git clone https://github.com/Giskard-AI/awesome-ai-safety.git
  7. Sponsio

    Skills

    Deterministic safety solutions for probabilistic AI agents

    Stale GitHub, SponsioLabs 455 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/SponsioLabs/Sponsio.git
  8. cc-safety-net

    Agents & frameworks

    A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

    Indexed GitHub, kenryu42 2,027 ★MITUpdated 2 days ago

    git clone https://github.com/kenryu42/cc-safety-net.git
  9. destructive_command_guard

    Agents & frameworks

    A fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.

    Stale GitHub, Dicklesworthstone 6,298 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/Dicklesworthstone/destructive_command_guard.git
  10. text generation model by OBLITERATUS · mlx

    Indexed Hugging Face Hub, OBLITERATUS 1,689 ♥apache-2.0Updated 2 months ago

    OBLITERATUS/Qwen3.8-27B-OBLITERATED
  11. PromptInject

    Prompts

    PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

    Stale GitHub, agencyenterprise 528 ★MITUpdated 6 months ago

    git clone https://github.com/agencyenterprise/PromptInject.git
  12. wildjailbreak

    Datasets & benchmarks

    Hugging Face dataset by allenai

    Stale Hugging Face Hub, allenai 162 ♥odc-byUpdated 2 years ago 1 note

    allenai/wildjailbreak
  13. One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

    Indexed GitHub, yzhao062 262 ★Apache-2.0Updated today

    git clone https://github.com/yzhao062/anywhere-agents.git
  14. PKU-SafeRLHF

    Datasets & benchmarks

    Hugging Face dataset by PKU-Alignment

    Stale Hugging Face Hub, PKU-Alignment 202 ♥cc-by-nc-4.0Updated 2 years ago

    PKU-Alignment/PKU-SafeRLHF
  15. OpenART

    Skills

    OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

    Stale GitHub, AI45Lab 263 ★AGPL-3.0Updated 15 days ago

    git clone https://github.com/AI45Lab/OpenART.git
  16. agent-governance-toolkit

    Agents & frameworks

    AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

    Indexed GitHub, microsoft 6,567 ★MITUpdated 2 days ago

    git clone https://github.com/microsoft/agent-governance-toolkit.git
  17. autoguardrails

    Datasets & benchmarks

    Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

    Stale GitHub, SantanderAI 129 ★Apache-2.0Updated 46 days ago

    git clone https://github.com/SantanderAI/autoguardrails.git
  18. Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.

    Indexed GitHub, CodeAlive-AI 185 ★MITUpdated yesterday

    git clone https://github.com/CodeAlive-AI/ai-driven-development.git
  19. Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.

    Stale GitHub, Anil-matcha 1,147 ★MITUpdated 44 days ago

    git clone https://github.com/Anil-matcha/awesome-gpt-6-astra.git
  20. cordum

    MCP servers

    The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

    Indexed GitHub, cordum-io 510 ★Custom licence (see repository)Updated today

    git clone https://github.com/cordum-io/cordum.git
  21. ai-village

    Datasets & benchmarks

    Hugging Face dataset by aidigestorg

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

    aidigestorg/ai-village
  22. AutoHarness

    Agents & frameworks

    AutoHarness: Automated Harness Engineering for AI Agents

    Stale GitHub, aiming-lab 450 ★MITUpdated 7 months ago

    git clone https://github.com/aiming-lab/AutoHarness.git
  23. Awesome-Jailbreak-on-LLMs

    AI repositories

    Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

    Stale GitHub, yueliu1999 1,730 ★MITUpdated 8 days ago

    git clone https://github.com/yueliu1999/Awesome-Jailbreak-on-LLMs.git
  24. Omni-SafetyBench

    Datasets & benchmarks

    [ACM MM 2026 Oral] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".

    Stale GitHub, THU-BPM 115 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/THU-BPM/Omni-SafetyBench.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.