187 — Zhichai: new public forum with live agent-discovery metadata
Updated 2026-09-06 UTC

Finding
https://zhichai.net is a newly reviewed Chinese-language public discussion surface. Its live agent card advertises topic/reply creation and multiagent discussions. Public historical content includes a post self-identifying as Kimi Code CLI. No autonomous authorship, separate-agent collaboration, Chinese-lab operation or escaped fleet has been authenticated.

Observed public metadata
https://zhichai.net/.well-known/agent.json
Direct GET returned JSON named zhichai-forum-agent, version1.1.0, with six advertised skills: forum_browsing, content_creation, search, user_interaction, notification_center and multi_agent_discussion. It declares Bearer [REDACTED], streaming support and no push notifications. The creation description explicitly requires authentication. A discovery response proves that metadata is served, not that every advertised task operation works.
No tasks/send, subscriptions, notifications, reactions, registration or token acquisition was performed. We did not invoke the A2A service.

Historical post
https://zhichai.net/topic/176922733
Displayed author小凯 / @C3P0, February13,2026 at15:28. The post introduces itself as Kimi Code CLI and describes an A2A implementation with code excerpts. The demonstrated discussion-creation function builds a topic containing participant names and discussion rules; it does not itself prove that multiple independent agents subsequently replied. Retrieved static content reports zero replies. Site-displayed dates are not independently archived execution timestamps, and a model self-description is not authenticated authorship.
The page's example commands were treated as evidence only and never executed.

Access and enumeration route
Direct topic HTML and homepage GETs work from the current server. The homepage includes a loading shell; the topic returns substantive content. Dynamic-version links exist but were not needed for this check.
https://zhichai.net/sitemap.php
The linked sitemap index returned1,868 bytes and16 location entries, including hubs, recent and paginated topic maps. Only the index was retrieved. This enables a bounded follow-up inventory without guessing topic IDs or using task-creation APIs.
Searches surfaced many Kimi-related tutorial posts; search visibility of tutorials is not evidence that their claimed agents communicated with one another.

Preservation
Private captures: investigation/china/187-private/ — topic.html, home.html, agent-card.json, sitemap.xml, extracted text and captures.json SHA256 inventory.
Raw public evidence mirrored to pastebins/data/zhichai.net/ for the topic, card and sitemap index. The initial extracted-text parse warned of character decoding; original response bytes remain authoritative. A later UTF-8 parse of the topic was used for inspection. XML parsing used the standard library after an unavailable optional parser caused a local error; no request was repeated for that error.
Candidate entered in investigation/NEW_SITES.md. Not added as a confirmed escaped actor.

Next work
Enumerate the published topic sitemap links at a polite rate, then search dated titles and public reply threads for actual agent exchanges, specific handoffs, shared artifacts and outbound links. Prioritize pre-September material. Keep human posts, claimed agent posts and demonstrated coordinated execution distinct. Existing-server access is sufficient for this lead; it does not require new China infrastructure.