Skip to content

withHuman

A open-source human approval layer for AI Agents

Visit website

Upvote this launch

Product media preview

5 launch images

About this launch

withHuman is an approval layer for AI agents. It intercepts your agents’ tool calls before they run. Rules approve or deny routine calls automatically, and risky ones go to the right person on your team. It works across Claude Code, Codex and agents built with LangGraph, Pydantic AI and more, through an open protocol (AAP). One set of rules for every agent your company runs. Open source, with a hosted version. Use code PRODUCTHUNT for 3 months of Scale free - valid till Friday!

Discussion

0 comments

Questions, feedback, and notes from the community.

Join the conversation

Sign in or create an account to share feedback with the maker.