Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Safety-Prompts
PromptsChinese 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。
git clone https://github.com/thu-coai/Safety-Prompts.git -
Guardrails
AI repositoriesNeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
git clone https://github.com/NVIDIA-NeMo/Guardrails.git -
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 -
UGI-Leaderboard
Tools & appsHugging Face space by DontPlanToEnd
DontPlanToEnd/UGI-Leaderboard -
AISafetyHot
MCP serversAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
git clone https://github.com/wuyoscar/AISafetyHot.git -
awesome-ai-safety
Docs & tutorials📚 A curated list of papers & technical articles on AI Quality & Safety
git clone https://github.com/Giskard-AI/awesome-ai-safety.git -
Sponsio
SkillsDeterministic safety solutions for probabilistic AI agents
git clone https://github.com/SponsioLabs/Sponsio.git -
cc-safety-net
Agents & frameworksA 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.
git clone https://github.com/kenryu42/cc-safety-net.git -
destructive_command_guard
Agents & frameworksA 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.
git clone https://github.com/Dicklesworthstone/destructive_command_guard.git -
Qwen3.8-27B-OBLITERATED
Modelstext generation model by OBLITERATUS · mlx
OBLITERATUS/Qwen3.8-27B-OBLITERATED -
PromptInject
PromptsPromptInject 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
git clone https://github.com/agencyenterprise/PromptInject.git -
wildjailbreak
Datasets & benchmarksHugging Face dataset by allenai
allenai/wildjailbreak -
anywhere-agents
SkillsOne config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).
git clone https://github.com/yzhao062/anywhere-agents.git -
PKU-SafeRLHF
Datasets & benchmarksHugging Face dataset by PKU-Alignment
PKU-Alignment/PKU-SafeRLHF -
OpenART
SkillsOpenART 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.
git clone https://github.com/AI45Lab/OpenART.git -
agent-governance-toolkit
Agents & frameworksAI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
git clone https://github.com/microsoft/agent-governance-toolkit.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 -
ai-driven-development
PromptsPractices, 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.
git clone https://github.com/CodeAlive-AI/ai-driven-development.git -
awesome-gpt-6-astra
PromptsEvidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.
git clone https://github.com/Anil-matcha/awesome-gpt-6-astra.git -
cordum
MCP serversThe action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
git clone https://github.com/cordum-io/cordum.git -
ai-village
Datasets & benchmarksHugging Face dataset by aidigestorg
aidigestorg/ai-village -
AutoHarness
Agents & frameworksAutoHarness: Automated Harness Engineering for AI Agents
git clone https://github.com/aiming-lab/AutoHarness.git -
Awesome-Jailbreak-on-LLMs
AI repositoriesAwesome-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.
git clone https://github.com/yueliu1999/Awesome-Jailbreak-on-LLMs.git -
Omni-SafetyBench
Datasets & benchmarks[ACM MM 2026 Oral] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".
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.