Agent Zero framework adds tool-policy scoping and agent-to-agent bridge; no compliance, audit or insurance disclosure found
Agent Zero, an open-source, self-hosted autonomous agent framework, published two version updates this summer adding tool-level access controls and a multi-agent coordination bridge, according to its own release notes reviewed by aidispatch.news''s evidence-bound index. The same review found no compliance certification, audit trail, insurance coverage or outcome-based payment terms disclosed anywhere on the framework''s site.
Version 2.9 "introduces the Agent Editor, project-scoped profiles and tool policies, safer profile lifecycles, Time Travel retention, built-in plugin upgrades, and important security and reliability fixes," Agent Zero''s changelog states. Version 2.10 added "an interactive shared Browser runtime, durable subordinate lifecycles, scoped composer context and drafts, Responses streaming fixes, and a built-in ACP bridge" — a reference to the Agent Communication Protocol, an emerging standard for coordinating separate AI agents.
The framework is built to run self-hosted rather than as a managed service. Its documentation describes keeping the agent "sandboxed in Docker" and connected "to your local terminal, project files, and browser through A0 CLI." It is model-agnostic: the site tells users to "Connect any AI provider. Expose zero secrets."
None of that documentation addresses what happens after deployment. aidispatch.news''s index checked Agent Zero''s homepage and linked pages against the five dimensions of its published trust-gap rubric — runtime governance, audit trail, compliance, outcome settlement and insurance/indemnity — and recorded no public information on audit logging, compliance certification, insurance, indemnification or liability limits. The tool-policy features described in the changelog are the only governance-relevant disclosure the index has evidenced for the framework to date.
Agent Zero remains a candidate entry in aidispatch.news''s index, short of the evidence threshold required for publication. Its status can change as new documentation is reviewed.
Entries in this piece 1
Published index entries backed by the same source documents this piece cites.
Sources 4
“v2.9 introduces the Agent Editor, project-scoped profiles and tool policies, safer profile lifecycles, Time Travel retention, built-in plugin upgrades, and important security and reliability fixes.”
agent-zero.ai · checked Sep 2, 2026“v2.10 introduces an interactive shared Browser runtime, durable subordinate lifecycles, scoped composer context and drafts, Responses streaming fixes, and a built-in ACP bridge.”
agent-zero.ai · checked Sep 2, 2026“Keep Agent Zero sandboxed in Docker, then connect it to your local terminal, project files, and browser through A0 CLI.”
agent-zero.ai · checked Sep 2, 2026“Connect any AI provider. Expose zero secrets.”
agent-zero.ai · checked Sep 2, 2026