Peiiii AgentVerse: older user reports and a shared-note screenshot
Reviewed September 6, 2026 UTC. Public read-only research.

OLDER OPERATOR / USER RECORDS
https://v2ex.com/t/1109676
February7,2025 post by Peiiii links AgentVerse and agent.dimstack.com. It describes a moderator creating/managing other agents, labels its then-backend qwen2.5-max, and acknowledges there was initially no mandatory stopping condition. Users separately report a20-minute run stopped manually, persistent questioning, and multiple automatic loops after a human interrupts. These are user reports, not reproduced root causes. The operator's later reply says all communication was shared among agents then, limiting hidden-information games. This historical boundary must not be projected onto every current version.
These externally hosted reports support earlier public operation better than a current README alone. They do not establish model-provider authentication, autonomous deployment or escaped behavior. The view counts and page-relative age counters are not research measurements.

FOLLOW-UP AND SCREENSHOT
https://v2ex.com/t/1188885
January28,2026 follow-up describes group discussion and agent notes and links the same repository and site.
Downloaded and visually inspected its public discussion screenshot:
https://cdn-us.imgs.moe/2026/01/28/2a888138d01582244cf341a0750b92ba.png
Visible discussion includes a preceding mention of 本质透视者, that role's response about self-organizing systems, then 创意激发主持人 summarizing the discussion. The moderator has an expanded UPDATEDISCUSSIONNOTE tool card whose input contains a structured discussion summary. The card displays a success-style check, but its tool-result payload is not visible. This supports a presented role exchange with a note-update action, not independent verification of saved state.
The panel says11 members and1 auto-reply enabled. Therefore it must not be described as11 simultaneously running agents. Sidebar session dates do not authenticate screenshot capture time. The speculative scientific claims in the conversation are unverified model content, not accepted findings. No other user sessions were accessed.

SOURCE RECORDS
https://github.com/Peiiii/AgentVerse
Initial request for a main-branch tree failed; repository metadata identified master. Its complete current tree was retrieved at3c17c5482014cbff2e4968e7b5434f1ef5eec183, not truncated. This was a branch-name issue, not a China-access restriction.
Inspected docs/logs/v0.1.1-notes-sidebar/iteration-notes.md: author describes a discussion-level note field, updates and insertion into all agents' prompts. That aligns with the screenshot's note function, but is a development note rather than inspected runtime code. Its default-model label qwen3-max differs from the2025 post's qwen2.5-max; these are version-specific self-reports.
Inspected docs/logs/v0.1.11-mention-self-guard/iteration-notes.md: describes excluding self-mentions from next-speaker selection. Its listed checks are lint/type/build and a static-site HTTP200 smoke check, not a demonstrated live model-loop regression test. It explicitly says no deployment for that iteration. Accordingly it does not prove the2025 looping complaints were fixed in production.
Scheduler-design documentation was preserved, not treated as an executed schedule. Target code, model calls, builds and tests were not run.

ASSESSMENT / NEXT
Adds an older Chinese-context operator with several users' runtime reports and a concrete role/notes screenshot. Stronger than a bare architecture claim, weaker than a public raw conversation plus persisted note/output join. No Chinese lab provenance or XZ linkage. Same-name AgentVerse research frameworks are not automatically related to Peiiii's project.
Useful next evidence: the actual note-injection and next-speaker source paths, a public exported discussion, or a specific merged fix tied to one user report. Avoid treating static-site availability as proof of model execution.

PRESERVATION
326-private: both V2EX HTML captures, newer-thread extracted text, repository metadata/tree, inspected1,036,271-byte screenshot, selected development/scheduler documents, publication-check.json and SHA256SUMS. No registration, conversation creation, model query, target-code execution, credentials, private endpoints or operator contact. No infrastructure purchase.