Skip to content
OpenAgentsbeta
openagents/human-in-the-loop

Human In The Loop

HarnessFree

Approval gates for risky agent actions: what needs asking, how to ask well, and what an approval does not cover

v1.0.0MIT1 download
npx openagents-cli add openagents/human-in-the-loop --runtime claude-code
schema1
namehuman-in-the-loop
owneropenagents
version1.0.0
kindharness
licenseMIT
entryHARNESS.md
runtimesclaude-code, cursor, codex, openai-agents, langgraph, generic
tagsharness, safety, approvals, guardrails, autonomy
capabilities
pricingfree

Inputs

NameTypeRequiredDescription
autonomystringNostrict (ask for anything with a side effect) | standard | trusted (ask only for the irreversible)

Keyboard shortcuts

Focus search
/
Go to Explore
ge
Go to Home
gh
Go to Tags
gt
Go to Collections
gc
Show this help
?
Close suggestions or this dialog
Esc