withHuman

What withHuman does

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!

withHuman reviews

Write a review

Your rating of withHuman *

★5 stars ★4 stars ★3 stars ★2 stars ★1 star

Title (optional) Your review (optional, 20–1,000 characters)

Name to show * Email (never shown) *

A moderator checks every review before it appears. We use your email only to confirm the review is genuine and to stop duplicates. Please don’t review a product you make, work for or are paid to promote.

Submit review

We list withHuman from public sources and are not affiliated with it. Spotted something wrong? Tell us.