NullRun is a runtime authorization layer for AI agents.
Control what agents can execute before actions reach production systems.
Allow, block, or require human approval.
AI agents are moving from generating text to taking real actions: calling APIs, changing customer data, sending messages, issuing refunds, and moving money.
NullRun exists to make those actions controllable at runtime.
We give teams a deterministic enforcement layer between an agent and the systems it can affect.
Our stack
Rust, Python, TypeScript, Next.js, PostgreSQL, Redis, REST APIs, WebSockets, MCP, and integrations with modern AI agent frameworks.
0 posts published
1 member
loading...
We're a place where coders share, stay up-to-date and grow their careers.
