Search

Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)

Research constitution and specification framework for comparing independently governed AI judgments without transferring authority.

Omega Walls v1 safety layer for RAG/agents

Tiny provider-neutral authorization checkpoint for AI-agent actions: allow / deny / require_approval.

Automated documentation system for Kali Linux tools using an AI agent. Scans, indexes, and documents your system tools automatically.

CLI-first, agent-native HTTP intercepting proxy & bug bounty toolkit. Headless Burp Suite alternative for AI agents (MCP), penetration testers, and ethical hackers with declarative YAML scope enforcement.

A passive policy-enforcement layer for agent tool calls

Contract-first agent runtime with execution pooling, chain composition, and pluggable orchestration

Agentic LLM injection benchmark — VisorCorpus payload delivery, VisorSD target discovery, HIT/MISS matrix per vector

Wi-Fi intrusion detection for the Raspberry Pi 4, monitor-mode 802.11 capture, an on-device ML classifier over 8 attack classes, and a bilingual (Arabic/English) dashboard with a tool-calling AI analyst, all from one FastAPI process.

A general-purpose agent framework that self-updates skills, rules, ethics, and identity from experience

A deterministic policy gate between an LLM agent and its tools: every call is allowed or denied by code before it executes, denied by default, and logged for audit.

Deterministic pre-execution safety gate for AI agents: verify tool calls against trusted evidence, policies, and WorldState before side effects.

Pi extension that masks sensitive data before it reaches the LLM and restores it for users and tools.

AI model: LayerFault/agent-mcp-contradictory-tool-annotation

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.

No description available

LangChain tools for Arbiter — pre-flight judgment for agents that hold a wallet.

Executable AI agent readiness gate: GitHub Action, prompt injection evals, LangGraph traces, risk profiles, and bilingual EN/中文 docs.

AIShell-Gate -- deterministic policy layer for AI generated Unix command execution. Policy gateway for AI agents executing shell commands. MCP server for Claude Code & Cursor. Tamper-evident audit