withHuman logo

withHuman

A open-source human approval layer for AI Agents

Listing details

HiCyou directory record

Listed
Listed website
withhuman.ai
Directory record created
Oct 16, 2026
Last record update
Oct 16, 2026

Listing information

  • Overview
  • 6 key features
  • 3 use cases

This page describes HiCyou's directory record. It is not a security, ownership, or product-quality certification.

Review the external site before sharing sensitive information or making a purchase.

withHuman preview

What is withHuman

withHuman is an open-source approval layer for AI agents. It intercepts agent tool calls before execution, automatically approving or denying routine calls based on rules and routing risky actions to the right person on your team. It works across tools like Claude Code, Codex, and agents built with LangGraph or Pydantic AI through an open protocol (AAP), letting companies apply one set of rules across all their agents. It is available as open source with a hosted version.

Key Features

Intercepts agent tool calls before they run
Automatic rule-based approval or denial of routine calls
Routes risky actions to the appropriate team member for human approval
Works across Claude Code, Codex, LangGraph, Pydantic AI, and more via the open AAP protocol
One shared set of rules for every agent a company runs
Open source with a hosted version available

Use Cases

  • Adding human oversight to autonomous AI agents before consequential actions execute
  • Defining centralized approval policies across multiple agents and frameworks
  • Escalating high-risk agent actions to the right person on a team

Why do startups need this tool?

Startups deploying AI agents need a way to let them do real work without giving up control over consequential actions. withHuman offers an open-source, protocol-based approval layer that works across frameworks, so teams can set one policy for every agent and keep humans in the loop where it matters.

FAQs

withHuman Alternatives

HumanLayer