Search

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).

Reusable Codex workflow kit and project generator for spec-driven agentic development.

🦞 Non-destructive upgrade tool for existing OpenClaw installations. Merges Clawdboss improvements without destroying your customizations.

Sistema de agentes especializados para Next.js + Supabase com validação automática de qualidade, segurança e arquitetura

AgentDNA: Verifiable and Auditable AI 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.

Compliance audit CLI: AST pattern matching + LLM agent loop + autonomous fix generation + audit-ready evidence

A Tool to give your LLM access to your Kernel.

SAFER SDK — instrument any AI agent framework with one line. Hooks for Claude SDK, OpenAI, OpenAI Agents, LangChain, Google ADK, AWS Strands, AWS Bedrock, and CrewAI.

Policy enforcement guardrails for OpenClaw-compatible agent frameworks

Autonomous red team for MCP servers. Sends adversarial payloads to your tools, proves exploitation, reports what's broken. 53 attack patterns across 6 categories. Zero dependencies. npx decoy-redteam

Linter, scorer, and evaluator for AI agent skill files (Agent Skills spec)

Service operation skills/workflows pack for Claude Code, Gemini CLI, and Codex

Scan AI agent skills for prompt injection and malicious code

SidClaw governance integration for LangChain.js — policy evaluation, human approval, and audit trails

CLI-утилита для интеграции CI/CD с платформой безопасности ASPM

An open-source SDK for AI agent safety

Autonomous cybersecurity execution agent for the terminal.

Multi-agent code review CLI powered by LLMs. Runs specialized agents in parallel to review GitHub PRs or local diffs.

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.