Search

Interven guard for Anthropic Computer Use — scan every computer/bash/text-editor tool call through policy + risk before it executes locally. Block, route to approval, or allow.

KYA (Know Your Agent) identity verification for LangChain agents

A penetration testing agent powered by local LLMs via Ollama

LangChain integration for the Kredo agent attestation protocol

AI model: dannyliv/agent-guard-deberta-pi-base

CLI tool to block --no-verify flag in git commands. Prevents AI agents from bypassing git hooks.

Autonomous Agentic Red-Teaming Swarm Protocol

Install and configure Lancelot — your AI-powered autonomous agent

AI model: AI45Research/AgentDoG-Qwen3-4B

An AI agent interrogation framework for identifying attack surface.

AI Agent Employees AI Agent Directory to Host All AI Agent Employees related AI Agents Services, Community, Reviews and More.

LlamaIndex integration for the Chio protocol -- capability-scoped FunctionTool and QueryEngineTool with vector-collection scoping

Embedded local LLM provider for wasmagent — node-llama-cpp adapter with grammar-constrained tool calling, multi-mirror download (HF/hf-mirror/ModelScope), and cert pipeline

v0.6 signing-time gate for Solana: decode any base64 tx offline, classify 37 danger primitives + Native Stake + bounded ATA/Memo recognition + a 14-program DeFi/NFT clear-signing registry, resolve ALTs and clear-sign Squads proposals with --rpc, optionall

Adversarial AI agent team for any project — installs Claude Code agents, hooks, and skills that enforce quality through productive friction

ExaAiAgent — Advanced AI-powered penetration testing framework with Docker sandbox, multi-agent workflows, and 50+ integrated cybersecurity tools.

Ed25519 signed decision receipts for kyegomez/swarms multi-agent systems. Wrap any tool in a Swarms agent with tamper-evident, offline-verifiable receipts in the Veritas Acta format (IETF draft-farley-acta-signed-receipts).

A governance-first multi-agent framework that treats agents as an organization, not just a router.

Drop Tulip's control runtime (admit() gate + tamper-evident audit) into the agent framework you already use — LangChain, LangGraph, CrewAI, the OpenAI Agents SDK, LlamaIndex.

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.