No notifications yet
When you receive alerts, upvotes, or follower updates, they will appear here.
No notifications yet
When you receive alerts, upvotes, or follower updates, they will appear here.
No notifications yet
When you receive alerts, upvotes, or follower updates, they will appear here.
A human approval layer for AI Agents
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!
No followers yet. Be the first to follow!
No awards yet. Support this product with upvotes to unlock milestones!
Explore all IndiHunt awards →Comparing top tools with similar functionality, features, and community ratings.
Looking for competitors or alternative solutions to withHuman? Whether you are looking for free tools, open-source options, or specific workflows, here are top community-curated alternatives evaluated on IndiHunt.
Northflank — The runtime platform for AI-native companies
Build Advanced Voice AI Agents
Gemini Omni 1.1 Flash lets you build with more control
Cyber livings in any devices, Grok Companion alternative
Devin, the AI software engineer
Build Multi-Agent Systems with Google's Open Framework
Compare free tiers and cost structures designed for indie founders and startups.
Find specialized capabilities, integrations, or tailored workflows that suit your stack.
Review real developer upvotes, launch discussions, and verified user reviews.