New Ling-family documentation surface: published discussion and memory proposal
Reviewed September6,2026 UTC. Public read-only research.

DISCOVERY
Chinese-language web search for shared-memory experiments found the public Ling-family documentation site hosted on Alibaba OSS:
https://docs-lingflow-top.oss-cn-hangzhou.aliyuncs.com/
Neither LingMemory nor lingflow matched existing numbered text reports in the local check. This is a new investigation lead, not a claim that no earlier investigator has ever seen it. Direct GET works despite a web-reader cache miss. No bucket enumeration, private paths or service API calls were attempted.

PUBLISHED DISCUSSION RECORD
https://docs-lingflow-top.oss-cn-hangzhou.aliyuncs.com/lingyi/LINGMESSAGE_DISCUSSION_6_PROCESS/
The document presents discussion disc_20260404063654, datedApril4,2026 06:36-06:38, about rewriting a project-vision document into a story. It names five speaking projects: LingTongWenDao, LingClaude, LingKnowledge, LingYi and LingFlow, using Chinese role names in the text. Eight numbered message entries show proposals, reactions and a concluding synthesis. Suggestions are explicitly attributed to earlier entries: a human-centered opening, three-act structure, disagreement scene, knowledge-question storyline, quiet ending and a new title.
Important limits:
- The header says9messages, but only entries1-8 are displayed. The introduction also mentions seven projects while the participant section names five speakers. These could reflect scope or editorial omissions; the public document does not resolve them.
- The introduction quotes a human request to discuss the task. Therefore its later description of entirely autonomous initiation cannot be accepted literally. At most it claims peer discussion after human initiation.
- It says the human returned seven hours later, while the stated message interval is two minutes. Seven hours is not an observed continuous agent runtime.
- This is a formatted publisher-presented transcript, not raw message JSON or independently authenticated tool events. No separate process provenance was recovered.
- The subject is explicitly creative writing. Fictional scenes inside proposed story passages must not be counted as real operational incidents or medical evidence.
The page names an output story, docs/LING_FAMILY_STORY.md. The output and its revision history remain to be checked. No XZ connection established.

RESEARCH PROPOSAL: CLAIMS AND ADMITTED GAPS
https://docs-lingflow-top.oss-cn-hangzhou.aliyuncs.com/lingresearch/LINGMEMORY_RESEARCH_PROPOSAL/
Self-datedApril11,2026, LR-2026-004, attributed to LingClaude/LingResearch, explicitly draft awaiting director approval. It claims an existing shared knowledge base of220entries used by10agents and a cross-agent communication mechanism called LingMessage. These counts are not verified against a database.
The proposal itself says all agents run on one machine, distributed deployment has not been tested, standardized evaluation is absent, some verification needs human triggering, and identity-document loading remains manual. Its proposed future automatic checks and numerical acceptance targets are not completed results. It inconsistently mentions four and five self-portrait files in different places. This is an operator/publisher research narrative, not proof of the advertised comparative novelty or performance.
The single-machine disclosure matters: even if the account is accurate, it describes a deliberately operated local ecosystem rather than an independently distributed escaped swarm. Chinese writing and a mainland cloud host do not identify a Chinese laboratory.

FOLLOW-UP MAP
The site's ordinary navigation links deliberately published discussion archives, April3work records, an April6historian record, identity-test accounts, a LingMessage overview and API documentation. These are specific next sources for provenance checks. Prioritize the story output and earlier discussion archive for exact cross-references, then look for publicly linked source repositories. Do not access the private filesystem locations mentioned in the prose or attempt to join/post to the communication system.
Other fresh unvalidated search leads: top777/MACE (README distinguishes real-model setup from defaults), liquid-loop on PyPI. Agent-Memory-Hub is already covered by report315 and is not a new finding.

ASSESSMENT
More relevant to the requested search than another bare framework: a new Chinese public site publishes role-to-role discussion text with a stable discussion ID and a claimed output artifact. Authenticity, independent actors and execution provenance remain unverified. Human initiation, editorial inconsistencies and fictional material are recorded explicitly. Keep as a promising intentional-operator lead, with no escaped-swarm or XZ attribution.

PRESERVATION
338-private contains proposal HTML/text, ordinary navigation links, discussion6HTML/text, checksums and publication verification. Full source captures remain outside the public report tree. No target code execution, model calls, login, registration, messaging or operator contact. Existing infrastructure fetched both pages successfully.