Agent Memory Hub: detailed handoffs are explicitly fictional
Reviewed September 6, 2026 UTC. Public read-only inspection.

RESULT
Agent Memory Hub is a concrete Chinese-context shared-memory project, but its inspected three-stage handoff demonstration explicitly did not invoke agents. Its detailed success/failure checklist must not be counted as an observed Claude Code-to-Codex-to-Wukong exchange.

PINNED REPOSITORY
https://github.com/liuyang0508/agent-memory-hub
Revision72d8aa1b2db94655644ca0bdb981882e0a132aaf; recursive tree not truncated;1,195 blob files. Metadata, tree and README preserved. The README describes local shared memory across coding tools and links a Gitee mirror. These features and Chinese-language documentation establish project context, not Chinese-lab or deployed-agent identity.

EXPLICIT DEMO DISCLOSURE
https://github.com/liuyang0508/agent-memory-hub/blob/72d8aa1b2db94655644ca0bdb981882e0a132aaf/docs/demo/00-scenario.md
The scenario labels its background fictional. It says no actual weather-cli code is written, no agent is really called, and snapshots are textual simulations of session state. The designed example passes a CSV-export task through coding, testing and PM communication, deliberately omitting a BOM/encoding decision to expose a handoff-schema weakness.

https://github.com/liuyang0508/agent-memory-hub/blob/72d8aa1b2db94655644ca0bdb981882e0a132aaf/docs/demo/handoffs/02-cc-to-codex.md
https://github.com/liuyang0508/agent-memory-hub/blob/72d8aa1b2db94655644ca0bdb981882e0a132aaf/docs/demo/handoffs/04-codex-to-wukong.md
Both contain source/target labels, May14 timestamps, concrete next actions and references to a DingTalk product group. Those identifiers and dates belong to the fictional demonstration. They do not prove real group messages, a real commit, model calls or task execution. No named private workspace or group was accessed.

https://github.com/liuyang0508/agent-memory-hub/blob/72d8aa1b2db94655644ca0bdb981882e0a132aaf/docs/demo/evaluations/eval-summary.md
The evaluation presents checked successes and failures, including alleged immediate resumption and a lost encoding decision, but later explicitly states that actual agent calls were not validated and the exercise concerns schema design. Read together, these documents are an illustrative design exercise, not a run transcript. This qualification applies to this demo, not automatically to every benchmark or implementation elsewhere in the repository.

ACCESS RESOLVED THROUGH THE REPOSITORY LINK
https://aihub0508.com/
The pinned README names this as the official website. Direct HTTPS returned200,199,532 bytes and title Agent Memory Hub 官网. This provides a working public route despite the www.fhsq.cn certificate hostname mismatch from report314. No certificate bypass or new geographic machine needed. The two hostnames' exact ownership/redirect history was not established.

SEVEN-AGENT SCAFFOLD SEARCH
Three searches used the exact phrase 3模型7Agent, the combination 7Agent/协作/超儿, and Chinese-word variants. No matching original scaffold repository or run artifact was returned. This bounded negative does not prove absence; the ZNT digest could omit the artifact name or paraphrase it. A result for openairymax/agentrt describes multi-model orchestration, but no link to the specific ZNT participant/scaffold was established.

NEXT
Move to other operators with public artifacts. The Memory Hub tree includes benchmark reports and implementation code that could be inspected separately, but do not spend further effort treating these explicitly fictional handoffs as a latent conversation archive. Search for voluntary run exports and references with verifiable source/target artifact joins.

PRESERVATION
315-private: metadata.json, tree.json, README.md, four pinned demo documents, official-site HTML/text, SHA256SUMS and publication-check.json. Raw captures stay private. No target software execution, model calls, registration, group joining or contact.