Search

Detect system prompt leakage in LLM model outputs via known patterns, configured-prompt substring matching, and unique fingerprint phrases. Python port of @mukundakatta/system-prompt-leak-scan.

Trust enforcement adapter for LangChain and LangGraph — powered by CapiscIO

Persistent knowledge graph for AI coding agents - 60-80% token reduction

A framework for managing agent trust, such as public vs. private computers.

Deterministic Agent Governance Gateway - Zero-Trust Policy Enclave for AI Agents

Portable OpenCode workflow plugins, explicit memory, and CLI tooling.

AI coding agent powered by Yiyan (文心一言) via browser automation — no API key needed

AI agent permission gateway - routes dangerous tool calls from Claude Code/Codex/Antigravity to your phone for approval

Cryptographic identity and trust for AI agents

AgentGuard installation entry point

A penetration testing agent powered by local LLMs via Ollama

AI model: dannyliv/agent-guard-modernbert-base

A ready to use http and https agent for working with proxies that keeps connections alive!

KYA (Know Your Agent) identity verification for CrewAI agents

CrewAI integration for Interven AI firewall. Scan every tool call your CrewAI agents make — block malicious requests, redact PII/secrets, route risky actions to human approval.

Local verifier for agentic data handoffs: envelope, provenance, trust, authority, identity, capability, and audit checks.

Interactive terminal UI for exploring AppThreat atom files with AI agent

Persistent memory system for Claude Code via Markdown. Setup with /init-project, resume with /catchup, wrap with /wrapup. Includes coding standards, MCP servers, and modular skills. Solves context loss after /clear.

Nakagai edge: the connector runtime that holds your broker credentials

AgentVisa credential presentation gateway