Search

OpenAI Assistants API integration for Interven AI firewall. Scan tool calls the assistant decides to make before your code executes them.

Score (query, document) pairs for vector/RAG poisoning signals: vector-text mismatch, instruction-like payloads, NaN, suspiciously round numbers. Python port of @mukundakatta/vector-poison-score.

Parallel multi-agent pipeline for code analysis and transformation.

LangChain integration for Interven AI firewall. Scan every tool call your LangChain agent makes before it executes — block malicious requests, redact PII/secrets, route risky actions to human approval.

Type-safe JavaScript dialect with runtime validation, sandboxed VM execution, and AI agent orchestration. Transpiles TypeScript to validated JS with fuel-metered execution for untrusted code.

CLI that runs Claude Code agents to autonomously scan, fix, and verify vulnerable dependencies

TypeScript SDK shim for My Compliance Center. Drop-in replacement for @anthropic-ai/sdk, openai, and @aws-sdk/client-bedrock-runtime with unavoidable governance enforcement.

Scan AI agent skills for prompt injection and malicious code

ATP Protocol is a payment-gated agent execution API that makes agent-to-agent payments and “pay to unlock results” easy on Solana, with a simple client integration (two endpoints + a Solana payment).

An open-source SDK for AI agent safety

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.

Official Python SDK for AgentShield — prompt injection detection for LLM applications.

CrewAI integration for the Chio protocol -- capability-scoped tools, per-role scoping, delegation attenuation

Interactive LLM agentic evaluation TUI for local and cloud models

A zero-dependency Claude Code PreToolUse guard that blocks destructive shell commands before they run.

An http(s).Agent implementation that block request Private IP address.

AI model: AI45Research/AgentDoG-Qwen3-4B

HackerAI — Your AI cybersecurity arsenal. Autonomous agent with 20+ free AI models, multi-provider rotation, and zero rate limits.

Universal AIGP (AI Governance Protocol) client — consent-based runtime AI governance

PikaKit — AI Operating System. 51 skills, 18 workflows, strict TypeScript.