Agent Control
Agent Control is the open source control plane for AI agents, built to establish a new standard for governing agent behavior at scale. It solves the problem of scattered, hardcoded checks by giving teams a centralized governance layer with step-level enforcement that can be managed from a single control plane and updated in real time without touching agent code. Developers can make any function governable by adding the control() decorator, turning meaningful decision points inside an agent into independently governed control points with their own policies. When a decorated function executes, Agent Control evaluates the input or output against the active policy and returns a decision: deny, steer, warn, log, or allow. If the decision is denied, the SDK raises a ControlViolationError before the unsafe action can proceed. Policies are decoupled from code, so developers decide where to place control hooks while policy teams decide what those hooks enforce.
Learn more
Onyx Security
Onyx is a secure AI control plane for discovering, protecting, governing, optimizing, and measuring AI agents and models across the enterprise. It gives security, governance, and AI teams visibility into sanctioned and shadow AI across SaaS, cloud, endpoints, and code, including prompts, responses, and agent actions. AI Security helps strengthen posture, identify vulnerabilities, and enforce real-time safeguards against threats and misuse, while AI Governance supports security standards and regulatory requirements with opt-in coverage and policy controls defined in natural language. AI Orchestration reduces friction when setting up agents and MCPs and helps optimize for cost, accuracy, and latency. AI ROI measures adoption, sets goals, and tracks outcomes across departments. The Onyx Guardian Agent acts as a supervisory AI that continuously identifies risks and remediates issues across the platform, helping organizations manage large numbers of agents at scale.
Learn more
Peta
Peta is an enterprise-grade control plane for the Model Context Protocol (MCP) that centralizes, secures, governs, and monitors how AI clients and agents access external tools, data, and APIs. It combines a zero-trust MCP gateway, secure vault, managed runtime, policy engine, human-in-the-loop approvals, and full audit logging into a single platform so organizations can enforce fine-grained access control, hide raw credentials, and track every tool call made by AI systems. Peta Core acts as a secure vault and gateway that encrypts credentials, issues short-lived service tokens, validates identity and policies on each request, orchestrates MCP server lifecycle with lazy loading and auto-recovery, and injects credentials at runtime without exposing them to agents. The Peta Console lets teams define who or which agents can access specific MCP tools in specific environments, set approval requirements, manage tokens, and analyze usage and costs.
Learn more
JetStream Security
JetStream Security is a security-first AI governance platform designed to give enterprises full visibility, control, and accountability over their AI systems by turning them from opaque, fragmented tools into managed, traceable infrastructure. It acts as a centralized control plane that connects identity, runtime governance, observability, and financial oversight into a single system, allowing organizations to “see every AI action, tie actions to accountable owners, [and] keep workflows inside approved boundaries” while enforcing policy at runtime. It introduces agentic identity, binding human, agentic, and non-human identities to specific actions and access permissions, ensuring every invocation, tool call, or workflow can be traced and governed through least-privilege access principles. Through continuous runtime governance, JetStream compares live AI behavior against approved blueprints, using immutable logging and real-time observability to detect drift.
Learn more
