withHuman
withHuman intercepts AI agent tool calls and enforces human approvals on critical actions, allowing routine tasks to be auto-approved by policy rules while directing risky decisions to appropriate team members. It supports popular AI agent frameworks via an open protocol (Agent Approval Protocol - AAP) and provides audit trails, notifications, and escalation paths. It's open source with a hosted option, aiming to make AI agents accountable in real work environments.
Ratings & Reviews
Write a reviewBe the first to share a thoughtful review.
Information
Website checks
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 18, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 70 out of 100, Needs improvement
- Accessibility
- 93 out of 100, Good
- Best Practices
- 100 out of 100, Good
- SEO
- 100 out of 100, Good
Website checks are queued. Results will appear here when complete.
Around the Web
Love that the protocol is an open spec and not just a product. Also appreciate the honesty about what you haven’t solved yet, like context for reviewers.
david_turner12 · Imported from Product Hunt
The production-fix story explains the need for this really well. An approval request needs enough context for someone to make a decision, so I'm glad you called that out as something you're still working on.
oleksii_sekundant · Imported from Product Hunt
This feels like a missing layer for production agents. How much context does the reviewer see before approving a tool call? Too little is risky, but too much gets noisy fast.
mia_qiao · Imported from Product Hunt