Open Source

A safety agent that integrates with your AI to detect and block threats in real-time.

Run coding agents in a clean, isolated sandbox with sensitive data redaction and observability.

An open-source AI agent that brings the power of Grok directly into your terminal.

Reasoning Augmented Generation. Query documents with full context, not chunked embeddings.

Open-weight guardrail models that run on your infrastructure with 50-100ms latency.

The universal allowlist for agents. Pre-scans packages, MCP servers, repositories, skills, web pages, and contributors for malware, prompt injection, and supply chain attacks.