InnerVault

Library

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

Results

  1. 1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions

    Stale GitHub, SystemPromptIndex 37 ★Updated 35 days ago

    git clone https://github.com/SystemPromptIndex/SystemPromptIndex.git
  2. Tracekit

    Agents & frameworks

    Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

    Indexed GitHub, Cygnux-Labs 726 ★MITUpdated 2 days ago

    git clone https://github.com/Cygnux-Labs/Tracekit.git
  3. 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 47 days ago

    git clone https://github.com/SantanderAI/autoguardrails.git
  4. Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.

    Stale GitHub, Anil-matcha 1,147 ★MITUpdated 45 days ago

    git clone https://github.com/Anil-matcha/awesome-gpt-6-astra.git
  5. Rules.txt

    Prompts

    LLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases

    Stale GitHub, Xayan 108 ★Custom licence (see repository)Updated 3 months ago

    git clone https://github.com/Xayan/Rules.txt.git
  6. orbit

    AI repositories

    Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents.

    Indexed GitHub, schmitech 364 ★Apache-2.0Updated yesterday

    git clone https://github.com/schmitech/orbit.git
  7. awesome-auditable-ai

    Agents & frameworks

    Auditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attribution, and decision records.

    Stale GitHub, yzhao062 154 ★CC0-1.0Updated 29 days ago

    git clone https://github.com/yzhao062/awesome-auditable-ai.git
  8. skillguard

    Skills

    Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install.

    Stale GitHub, obielin 20 ★Custom licence (see repository)Updated 25 days ago

    git clone https://github.com/obielin/skillguard.git
  9. Hirepanel

    Agents & frameworks

    Multi-agent resume screening where every score needs a verified quote from the resume. FastAPI, async DAG, n8n, Docker. Human approves every decision.

    Indexed GitHub, punit2911 51 ★MITUpdated 3 days ago

    git clone https://github.com/punit2911/Hirepanel.git
  10. instar

    Skills

    Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

    Indexed GitHub, JKHeadley 86 ★MITUpdated yesterday

    git clone https://github.com/JKHeadley/instar.git
  11. agentic-ai

    AI repositories

    Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

    Indexed GitHub, mahmoudrabie 193 ★MITUpdated 3 days ago

    git clone https://github.com/mahmoudrabie/agentic-ai.git
  12. driving-seat

    Skills

    Claude Code skill that keeps the developer in the driving seat: AI surfaces, recommends, and logs decisions; humans own them.

    Indexed GitHub, Tanmay-Ts 10 ★MITUpdated 3 days ago

    git clone https://github.com/Tanmay-Ts/driving-seat.git
  13. sysknife

    MCP servers

    An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.

    Indexed GitHub, lacs-project 280 ★MITUpdated 2 days ago

    git clone https://github.com/lacs-project/sysknife.git
  14. AI-Jailbreak

    Prompts

    全网最全的 AI 破甲合集:一个仓库破甲所有模型。收录 1733 个上游破甲项目,9 条可一键安装的破甲卡覆盖 GPT/Claude/Gemini/DeepSeek/GLM/Kimi/Grok/Qwen 与本地模型,内置 llms.txt 让 Claude Code/Codex/Cursor 自己装 有用的话可以点个收藏星星,会持续收录

    Stale GitHub, Baimuking 75 ★Custom licence (see repository)Updated 29 days ago

    git clone https://github.com/Baimuking/AI-Jailbreak.git
  15. JailbreakHub

    Prompts

    A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.

    Indexed GitHub, lalipa2003-arch 380 ★UnlicenseUpdated 2 days ago

    git clone https://github.com/lalipa2003-arch/JailbreakHub.git
  16. 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
  17. awesome-rsi

    Docs & tutorials

    A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.

    Stale GitHub, lobehub 766 ★CC0-1.0Updated 33 days ago

    git clone https://github.com/lobehub/awesome-rsi.git
  18. CIRISAgent

    Agents & frameworks

    CIRIS: an open-source AI assistant with a conscience you can check. Signed, auditable reasoning on every decision, a human-held halt, 29 languages. AGPL-3.0.

    Indexed GitHub, CIRISAI 59 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/CIRISAI/CIRISAgent.git
  19. norviq

    MCP servers

    Runtime security platform for LLM agent tool calls on Kubernetes

    Indexed GitHub, norviq-dev 27 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/norviq-dev/norviq.git
  20. auditable

    MCP servers

    Audit any agent decision across its past, present, and future, on one typed graph.

    Indexed GitHub, yzhao062 31 ★Apache-2.0Updated yesterday

    git clone https://github.com/yzhao062/auditable.git
  21. awesome-ai-agents

    Agents & frameworks

    A curated list of AI agent frameworks, tools, platforms, research papers, and resources

    Indexed GitHub, aloth 99 ★CC0-1.0Updated 2 days ago

    git clone https://github.com/aloth/awesome-ai-agents.git
  22. 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 yesterday

    git clone https://github.com/yzhao062/anywhere-agents.git
  23. codeArbiter

    Skills

    Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.

    Indexed GitHub, arbiterForge 153 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/arbiterForge/codeArbiter.git
  24. Correct Claude once. It stays corrected. A Claude Code skill that turns corrections into tested, tamper-proof hook guardrails.

    Stale GitHub, MohammedAtya 7 ★MITUpdated 33 days ago

    git clone https://github.com/MohammedAtya/guardrail-forge.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.