Crewship
Crewship is the developer-first platform for deploying AI agent workflows. Deploy your CrewAI, LangGraph, and LangGraph.js agents with a single command and watch them execute in real-time. Key features include one-command deployment, real-time execution streaming, artifact management, auto-scaling, version control, and encrypted secrets management. Crewship handles infrastructure so developers can focus on building great AI agents. Multi-framework support with AutoGen, Pydantic AI, smolagents, OpenAI Agents, Mastra, and Agno coming soon.
Learn more
CyCraft XecGuard
XecGuard is CyCraft’s LLM Firewall for trustworthy, agentic AI, designed to protect enterprise AI systems from prompt injection, jailbreak, prompt extraction, data leakage, unsafe outputs, and agentic workflow risks. Built on CyCraft’s red teaming and blue teaming experience across government, finance, and high-tech manufacturing, XecGuard goes beyond model-level defenses by combining AI guardrails, cybersecurity controls, compliance protection, and risk response strategies for real-world enterprise AI adoption. It is positioned as a plug-and-play LoRA security module that can strengthen LLM defenses without requiring changes to the underlying model architecture, helping teams add protection quickly while preserving performance. XecGuard is built on proprietary security datasets and multi-stage fine-tuning techniques, enabling LLMs to better resist adversarial prompts, malicious manipulation, and attempts to extract protected instructions or sensitive information.
Learn more
Vulnify
Vulnify is runtime authorization for AI agents. Before a sensitive tool call runs, your code calls check() and gets ALLOW, REVIEW or BLOCK, with a 0-100 risk score and the reasons: action, data sensitivity, destination, volume. REVIEW pauses only that action until a person approves. Start in monitor mode, fail closed by default. Policies as code, Node and Python SDKs (MIT) with LangChain, MCP, CrewAI and LangGraph adapters, and a hash-chained audit log with JSON/CSV export. Free plan available.
Learn more
F5 AI Guardrails
F5 AI Guardrails is a runtime AI security solution designed to protect AI models, applications, agents, and connected data throughout deployment and operation. The platform helps organizations defend against adversarial threats such as prompt injection, jailbreak attacks, harmful outputs, and unauthorized AI behavior. It provides real-time monitoring and enforcement of security policies to prevent data leakage, compliance violations, and misuse of AI systems. Organizations can implement predefined guardrails or create customized policies tailored to specific business requirements and AI use cases. The platform also delivers observability, auditing, and governance capabilities that help organizations maintain visibility into AI interactions and regulatory compliance. By combining threat protection, data security, and AI governance, F5 AI Guardrails helps enterprises operate AI systems more safely and responsibly.
Learn more
