Arnav Gupta launched Prismor to govern AI agent tool calls

The open-source runtime intercepts tool calls from Claude Code, LangChain and other agents, applying policy before commands execute.

By · Published

Primary source: Arnav Gupta on X

Why it matters

Agents are gaining access to shells, files and production APIs faster than companies are building controls. Prismor gives Gupta an open-source wedge at the point where agent output becomes action.

Illustration of Prismor intercepting tool calls from agents such as Claude Code and LangChain and checking them against policy before commands execute.

Arnav Gupta (@_ar9av) launched Prismor on July 6th as an open-source control plane that sits between AI agents and the tools, files and services they can reach. The bet is that enterprises need a security checkpoint at the moment an agent attempts an action, rather than another dashboard explaining what happened afterward.…

Reader comments

Conversation for this story loads after sign-in.