withHuman
Open-source human approval layer that intercepts agent tool calls and routes risky ones to people.
Visit withHuman ↗Pricing
- Model
- freemium
- Starting price
- $20/user/mo
- Source
- Pricing page ↗
Niches
Best for
Trace, debug and evaluate agents
▸ Policy rules plus human review for consequential agent actions, with full audit trail.
Run agent-generated code in a sandbox
▸ Hooks for Claude Code/Codex and AAP SDKs so risky tool calls wait for approval.