AI Safety
Top open-source AI Safety AI systems, agents, and MCP tools.
Discover and install verified AI Safety AI systems, autonomous agent skills, and Model Context Protocol servers on AIStoreHub. Reusable, security-scanned, and ready for 1-click execution in Cursor, Claude Code, and terminal workflows.
Available AI Systems & Skills (8)
Open in Advanced FilterUnified Rust framework for building, verifying, and testing web apps. Kernel-based architecture for Lean 4 verification and GPU acceleration. Built-in red-teaming tools for automated vulnerability detection.
A filesystem-native governance layer for AI agents. Folders are rules, counters are activation, Git is the audit trail.
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
Automated Proof-of-Carrying Change Management for AIOps 2026
Build & Monetize for AI Safety
Have you created an autonomous agent, MCP server, or Claude Code skill for AI Safety? Publish it to AIStoreHub with dual-currency checkout (USD $ + INR ₹) and earn 85–90% net revenue.