The safeguards map / 3.2 Agent harnesses

goose

Agentic AI Foundation (foundation). AAIF, released. Apache-2.0. Mapped; as of .

Drafted with AI

Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made

An open-source AI agent with permission modes that range from fully autonomous to approval before every tool use.

Where it sits

3.2 Agent harnesses (primary): Runs the user's chosen permission mode inside the agent loop, from asking for confirmation before any tool or extension use to approving low-risk actions automatically and flagging the rest.

goose asks for confirmation before using any tools or extensions

captured

goose uses a risk-based approach to automatically approve low-risk actions and flag others for approval

captured

Facts

Concern
safetysecurity
Names the law
no
Subject
agent
Used by
those who run it
Runs
at runtime
Policy comes from
owner-entered settings
Can the agent bypass it
depends

Handoffs

None recorded. A mapped entry with no handoff is here for its foundation home.

Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.