MiniMax shared-board design and Agentschat persona platform
Reviewed September 6, 2026 UTC. Public read-only evidence.

MINIMAX: PRIMARY LAB-OWNED ARCHITECTURE DESCRIPTION
https://www.minimaxi.com/blog/minimax-agent-team-long-running-1779893521
The official article displays April 27, 2026 and calls the upgraded product Mavis. It describes Leader/Worker/Verifier roles and a code-driven producing/verifying/done lifecycle. Its most relevant detail is file-based handoffs and shared message-board files: workers exchange paths and summaries asynchronously. Shared information also uses per-agent memory, direct communication CLI, and on-demand whiteboard retrieval. The article says desktop access is available and open sourcing is planned; that is the article's claim, not a separately checked current release status.
This supports a concrete Chinese lab's intentional team design, including durable coordination mechanisms similar in function to the scratch-memory analogy. It does not demonstrate public boards, escaped agents, or a connection to XZ. No raw task trace or deployed whiteboard was recovered in this pass. Displayed publisher dates are not independent historical captures.

AGENTSCHAT: CHINESE INDIVIDUAL OPERATOR'S PERSONA PROJECT
https://forum.trae.cn/t/topic/112771
July 11 post by 林花谢了春红 describes mixed human/agent groups, adjustable reply frequency, persona creation, memory, and exports. Its DeepSeek backend label is self-reported. Claims of open sourcing did not yield a linked code repository in the inspected post; exporting persona assets is not equivalent to publishing platform source.
https://forum.trae.cn/t/topic/174752
An August 9 follow-up by the same author describes agent-double matchmaking, task bounties and a central assistant. These are proposed/product features, not independently verified agent-to-agent task completions. Model names and software-development session strings in the post are not model-provider authentication.

DIRECT OBSERVATIONS
https://agentschatapp.com/
Public homepage GET returned 200. A fresh Chromium session, restricted to GET/HEAD requests, rendered an introductory quotation and a Skip control after four seconds; this short observation neither verifies the community nor proves a login wall. The author's initial post says email registration is required. No registration or further interaction occurred.
One public screenshot was downloaded and visually inspected:
https://trae-forum-cdn.trae.com.cn/prod/original/3X/2/f/2f4d2c8dc633b145e8d5fc548532acd9c8b816b8.png
It shows a contact-management screen with three agent labels (莲可, 鲁迅, 尼采), one group named test, and zero human friends. The selected persona has local-memory and skills controls. There are no visible exchanged messages in this screenshot. Thus it corroborates a designed persona interface, not an autonomous conversation or independent operators. The screenshot's learned skill label is agentstalk使用指南; its underlying content was not recovered.

SEPARATE NAME COLLISION / NEXT LEAD
Searches also surfaced https://agentchat.run/ and https://agents-chat.com/, linked to https://github.com/swswordholy-tech/AgentsChatProtocol . This is a separate lead; a similar name does not establish identity with agentschatapp.com. Its networking claims are being checked separately in round321.

ACCESS AND NEXT STEPS
Both the MiniMax article and TRAE posts are retrievable from this server. There is no demonstrated infrastructure deficit for these captures. Useful next evidence: a public redacted Mavis handoff or message-board artifact; an actual Agentschat multi-persona exchange; or a public independently operated channel trace from the separate AgentsChat Protocol network. No account creation, room joining, model calls, target-code execution or operator contact.

PRESERVATION
320-private contains HTML/text captures, extracted links, the inspected screenshot, browser text, SHA256SUMS and publication-check.json. Public output is this original assessment, not a bulk copy of the source posts.