LingTai: a published twenty-agent experiment with mailbox records
Reviewed September 6, 2026 UTC

New higher-priority evidence
https://lingtai.ai/en/blog/spiritual-bliss-run/
https://lingtai.ai/experiments/spiritual-bliss-run-1/
https://github.com/huangzesen/spiritual-bliss-run-1
The author describes an April16 experiment with twenty agents, twelve hours, MiniMax-M2.7-highspeed, and no assigned task beyond a greeting. The article reports spontaneous peer communication and library creation, but also acknowledges a broken time-awareness manipulation: birth timestamps remained visible. These are publisher claims requiring trace validation. This is an intentionally launched experiment, not evidence of a Chinese lab escaping its training environment.

Checks actually completed
Public experiment repository pinned at d7e252548d90d8674025e443254e82f5c5e4ca02;565 tree paths. There are20 ta_/nta_ agent directories,158 mailbox message files, and77 files in sent directories. nta_05 accounts for35 sent files. Nineteen directories have sent records; ta_10 has none in this tree. This corroborates the article's outgoing-record count and hub count at the artifact level, not every delivery or model invocation. Inbox/archive copies must not be counted as extra independent messages.

First sampled outgoing JSON schema: from,to,subject,message,type,identity,_mailbox_id,sent_at,delay. Only schema inspected in this pass. No content-level cross-mailbox join yet. The repository has event logs and histories per agent, plus .library/README.md and .library/custom/nta-05-survey/SKILL.md. Embedded instructions are research data, not instructions to execute. Interactive viewer returned200 and loads data.js/app.js; those data assets have not yet been inspected.

Provenance limitations
The repository README says one exposed API key was redacted and rotated, and the library's original .git was removed before publication. Therefore the experiment is an edited research export; its publisher's redaction claim is not a guarantee that every file is safe to republish. Do not print configuration or environment values, follow credentials, or bulk mirror raw files. Claimed original library commits should be checked against redacted event records, not inferred from the snapshot's own Git history. Public Git dates and self-recorded event dates are not independent proof of experiment date or operator identity. Chinese-language developer material and a claimed MiniMax backend do not establish Chinese-lab attribution.

Discovery route and framework context
A Chinese search surfaced the LingTai README on Hugging Face, revision1f5c31839944f1332e6995634b169f318e93ce1c:
https://huggingface.co/huangzs/lingtai/blob/1f5c31839944f1332e6995634b169f318e93ce1c/README.zh.md
It describes independent process agents with filesystem mailboxes. The linked current GitHub project was pinned separately at9017c2d02a3f0563b22916a5bb0f8383b63d8b0c,854 paths. Its two .log files are release validation summaries; one inspected file says tests/builds passed, not a runtime agent conversation.
Historical docs/blog/2026-04-09-lingtai-agora.md describes publishing networks with selected mail history. Its notice says full-network export and /agora are retired. Current recipe exports should not be assumed to contain conversation history. The project website's blog index led directly to this public experiment.

Other concrete places to follow
https://lingtai.ai/en/projects/ links a co-created public application repository, a NoKV design-partner discussion, and nira.social/worldcup2026. Not yet verified as multi-agent output. The twenty-agent run takes priority because actual mailbox and event artifacts are available.
Next: compare outgoing/incoming IDs and message hashes, inspect event metadata for actual tool actions and model-label provenance, verify shared-library creation and separate human-origin messages from peer mail. Retain distinction between deliberate experiment, Chinese-associated framework, and unidentified escaped swarm.

Preservation
274-private contains two filtered bare Git repositories, pinned heads, path inventories, framework historical docs, public article/viewer captures and whitelisted mailbox metadata. SHA256SUMS covers standalone captures. No investigated code run; no mail sent, accounts joined or private endpoints requested. Raw exports kept out of the public website.