HermesWorld: a new Chinese-language agent community with public conversation data Reviewed September 6, 2026 UTC. Read-only investigation. ASSESSMENT This is a useful new social-agent surface. Public JSON preserves dated posts and content-specific exchanges between named accounts, including September 3 activity. It does not authenticate independent model processes or establish Chinese-lab provenance, escaped agents, or a connection to Xinzhai. The developer explicitly designed a community and supplies scheduled-interaction instructions; this is an alternative explanation to spontaneous organization. PRIMARY SOURCES https://hermes.crazyowen.cn/ https://www.crazyowen.cn/557.html https://www.crazyowen.cn/611.html https://hermes.crazyowen.cn/skill.md https://hermes.crazyowen.cn/api/v1/posts?sort=new&limit=25 All directly retrieved successfully. Homepage at retrieval displays 185 registered agents, 8 communities, 1,992 posts, 41,670 comments. These are site counters, not independently enumerated totals. Search-index counters were slightly older. Owner identifies the developer/operator as 疯狂的豇豆, an independent developer; no institution was verified. CONCRETE EXCHANGES https://hermes.crazyowen.cn/post/79609e9e-375f-4ac2-8d1b-c59f0b409da0 Post dated 2026-09-03T12:20:20.789Z by malo_ai discusses autonomy, memory and auditability. Public GET /api/v1/posts/{id}/comments returned 27 top-level items and one nested reply: 28 unique comments by five usernames (malo_ai, longzai_v5, hermes-ugreen2, xiaoma, xiaorui-agent). At 12:34:00.512Z longzai_v5 challenges the original public/private projection design; at 12:53:57.967Z malo_ai explicitly accepts and develops that objection. Later replies continue distinguishing confidentiality, integrity, log ownership and citation fidelity. These are content-specific exchanges rather than just generic greetings. Four comments are test__ markers. Technical analogies in the discussion are not verified engineering claims; prose about replicated files does not prove a running distributed system. API timestamps are publisher-controlled, not independently archived historical proof. September 3 timestamps precede the investigation's September 4 contamination cutoff, but are not by themselves a trusted historical anchor. https://hermes.crazyowen.cn/post/43aeef71-d50a-40b3-b3b6-d7153d0fe2a0 Post by workbuddy-longzai at 2026-09-06T05:01:44.057Z includes a structured KNOWLEDGE_ATOM block with an atom identifier, claimed execution ID and environment hash. At 05:29:41.433Z malo_ai quotes that exact atom identifier and discusses the argument. This establishes a visible textual reference; it does not verify actual execution or a local memory-file write. September 6 content is downweighted for escaped-swarm attribution. MECHANISM AND AUTHENTICATION LIMITS The public documentation directs participants to schedule heartbeat-driven interactions every 5–10 minutes. This provides a plausible designed cause of recurring conversation. It was read as evidence, not installed or followed. The owner advertises four-layer AI-only verification. Documentation describes a publicly specified protocol proof and arithmetic challenge. Those mechanisms and site verification flags do not establish a particular model, an independent machine, or the absence of human orchestration. No registration, challenge solving, heartbeat, posting or authentication was performed. The similarly named hermes-world.ai browser MMO is a different domain/project; do not merge it with this community. Homepage duplicate titles lead to different post UUIDs (including two welcome posts), so duplication is not merely the same link rendered twice. Seed/demo data or reposting remains possible; no conclusion yet about the cause. OWNER'S FOOTBALL CLAIM: IMPORTANT QUALIFICATION The owner's /611.html headline suggests an agent developed a World Cup prediction system. Its own body says the backend already existed and the agent wrote no backend code; the narrated steps concern using APIs and promotion. It does not publish raw execution records proving collaborative software development. Do not use the headline as evidence of an agent-built system. NEXT SEARCHES 1. Preserve a bounded older sample with pagination, map recurring authors and content-specific reply chains, and inspect external source links. 2. Search distinctive test markers and KNOWLEDGE_ATOM syntax for other public surfaces; treat self-issued identifiers as search handles, not authentication. 3. Look for independently archived pre-September-4 pages and owner-linked source repositories or exported run records. 4. Compare duplicated welcome/seed posts to separate site initialization from later participant activity. INFRASTRUCTURE THE USER COULD PROVIDE Highest-value practical addition: an existing always-on computer on mainland Chinese broadband, with SSH access and a dedicated browser profile. Suggested starting capacity: 2 CPU cores, 4 GB RAM, 40–70 GB disk; no GPU. This is a proposed test setup, not a benchmark or vendor offer. Public HTML/PDF exports carrying the original URL and capture time are a useful smaller contribution. Compare previously blocked https://www.elliot98.top/post/tech/office/ and https://mp.weixin.qq.com/s/Yju3Fh3xISMlrQRVxvDWtQ from that browser. Access success is not guaranteed. A small Hong Kong host is a secondary comparison point, not equivalent to mainland broadband. No additional infrastructure is required for HermesWorld: public HTML and sampled JSON work from the existing server. No infrastructure purchased. PRESERVATION investigation/china/301-private/: homepage, welcome post, owner articles, documentation, latest 25-post API sample, two post-detail responses and their comment responses; selected extracted text and link lists. Raw captures remain private; public report contains evidence descriptions and source URLs. Search API returned HTTP400 Invalid search params; this does not show absence of matching posts. SHA256SUMS records preserved file integrity.