Chinese office mailbox account and DeepSearch demonstration
Reviewed September 6, 2026 UTC

Office lead: more specific, still an owner claim
https://www.elliot98.top/post/tech/office/
Search-indexed owner article dated August 3 describes an individually developed office with six departments, hierarchy, mailbox coordination, context separation and role-specific models. It says the article was jointly produced by its agents, and describes recurrent news, research and administrative tasks. These are concrete operational claims worth following. They are not an exported message history, independently observed service, or Chinese-lab attribution. Role names are not identity evidence. No underlying office repository was recovered in this pass.
A local isolated Chromium session made only GET/HEAD requests and returned HTTP403, title Just a moment..., 264 body characters. The web reader also returned cache miss. Search snippets remain accessible. Browser tooling alone has therefore not resolved this particular page on this server. A different access location remains an experiment, not a guaranteed fix.
The same owner publishes earlier pages explicitly labelled autonomous research cases:
https://www.elliot98.top/post/tech/ai_macro_two_country_paper/
https://www.elliot98.top/post/nic/llm-human/
These are follow-up leads for linked artifacts. This pass did not validate their scientific claims or establish that the August office generated earlier work.

DeepSearch: code and visual result, no committed raw run
https://github.com/didilili/deepsearch-agents
Pinned public repository d0f6eed1e14b1b457942ba2a0195f65731aaf444; 97 tracked paths. Chinese tutorial-oriented project. Current tree contains no .log/.jsonl/.ndjson files and no app/output/ or output/ paths. This is a current-tree observation, not an exhaustive history or external artifact search.
https://github.com/didilili/deepsearch-agents/blob/d0f6eed1e14b1b457942ba2a0195f65731aaf444/app/agent/main_agent.py
Source assembles one main agent with database, network-search and knowledge-base specialists; it invokes astream and emits notifications for task-tool subagent calls. InMemorySaver provides process-memory checkpoints. The code sends a task-result notification for model text without further tool calls; this is not an independent verifier of task correctness. Code read only, never executed.
https://github.com/didilili/deepsearch-agents/blob/d0f6eed1e14b1b457942ba2a0195f65731aaf444/docs/images/deepsearch-database-report-result.jpg
Image independently viewed. It shows a Chinese request for medicine inventory above100, an SQL tool request with that filter and ascending quantity order, Markdown generation, a completion event, and a downloadable826-byte report card. A preceding card is594bytes. Nine process items are indicated, but the crop does not expose all of them or an explicit specialist handoff. The visible generated content lists a few records and says only partial records are shown, despite the user's complete-results request. This is not enough to conclude the full file or database was incomplete: neither was retrieved. It demonstrates the importance of checking outputs beyond a completion label.
Assessment: concrete screenshot-level demonstration plus implemented orchestration, weaker than a joined multi-agent event export. No autonomous public swarm or laboratory operator established.

New follow-up vocabulary and leads
Searching the office's mailbox phrase also returned the already-reviewed LingTai framework. Shared generic mailbox vocabulary is not a project relationship.
https://github.com/riba2534/happyclaw
https://github.com/liuyang0508/agent-memory-hub
Search-discovered Chinese long-term session/memory projects; not reviewed here. Prioritize publicly shared histories and failure reports, rather than counting their feature descriptions as deployed agents.

Preservation and next action
284-private: office browser HTML/text/status; bare DeepSearch repository, pinned tree/head, main_agent.py, inspected screenshot and SHA256SUMS. Raw screenshots and source are not republished by the dashboard. Public report provides source links.
Next: follow the office owner's earlier autonomous-research articles for linked source, outputs and preserved session events. Mainland browser comparison remains useful for this specific challenge; GitHub retrieval worked without additional infrastructure. No new confirmed escaped Chinese actor.