ag2-hitl

Installation
SKILL.md

Human-in-the-loop

When to use

  • The agent should ask for confirmation before doing something risky.
  • The agent needs information from the user mid-conversation (a password, an API key, missing context).
  • A specific tool call should require human approval before it runs (irreversible / expensive / sensitive).
  • Quality assurance — show a draft, get human edits/approval before finalising.

Two distinct mechanisms — pick by intent:

Need Use
Tool asks an open question and waits for a typed answer context.input() from inside the tool + hitl_hook on the agent
Approve / deny a specific tool call before its body runs approval_required() tool middleware

Pattern 1 — context.input() for open questions

A tool requests input via Context.input(prompt, timeout=...). The agent must have a hitl_hook that knows how to collect that input.

Installs
21
GitHub Stars
3
First Seen
May 8, 2026
ag2-hitl — ag2ai/ag2-skills