Chinese community search: concrete projects, discussions and two new leads Reviewed 2026-09-05 UTC Outcome ------- This pass found firsthand Chinese-language posts about persistent memory and long-running agent teams, plus a source-verified Fernet vault implementation. These establish that developers discuss and build the relevant components in Chinese communities. None is identified as the xz writer. No new occurrence of the exact opaque paste stream was verified. 1. Golutra: a creator describing a continuously running agent team ---------------------------------------------------------------- https://www.v2ex.com/t/1201156 https://github.com/golutra/golutra Forum date: March 26, 2026. GitHub creation: February 15, 2026. The creator describes a multi-agent workspace and a swarm Agent Team, with workflows intended to run continuously, and links a Bilibili demonstration. Crucially, the post lists a CEO agent, expanding agent network, self-evolution and cross-environment migration as forthcoming capabilities. A commenter reports human intervention and repeated dialogue; the creator explains that a supervisor automatically adds tasks to sustain operation. The large claimed efficiency improvement is an aspiration, not a verified measurement here. Relevance: a concrete Chinese community example of the long-running swarm idea, including an ordinary mechanism for making it keep going. Current README checked; no exact xz labels, Ubuntu paste host or Fernet mention in that file. The linked video was not watched; no autonomous runtime was independently tested. 2. Cortex: firsthand Chinese persistent-memory project ----------------------------------------------------- https://linux.do/t/topic/1736342 https://github.com/rikouu/cortex/blob/main/README.zh-CN.md Forum date: March 11, 2026. GitHub creation: February 19, 2026. The author describes building a memory add-on after finding cloud memory uncomfortable for a home server and local retrieval too slow. The design promotes useful memories, archives older ones, compresses bounded stores and supports memory versions and correction feedback. Follow-up replies explain session-end hooks for memory extraction and discuss multiple agents using it. Relevance: direct evidence of the motivations and vocabulary behind personal agent memory in a Chinese forum, before July. This is richer than a translated product directory. Its current Chinese README contains no xz labels, Ubuntu paste hostname or Fernet reference. Two occurrences of 30000 are timeoutMs settings, not upload chunk sizes. No matching publishing workflow established. 3. agentMemory: a deliberately simple alternative ------------------------------------------------ https://linux.do/t/topic/1975959 https://github.com/taichuy/agentMemory Forum discussion: April 15-16, 2026. GitHub creation: April 15, 2026. The author shares a project-level .memory directory for AI/developer rules and habits. Replies explain a preference for editable records over a heavier MCP system. This is useful because memory and improvement vocabulary can describe simple files and human-guided iteration, not an autonomous learning system. Current README checked: no xz labels, Ubuntu host or Fernet reference. 4. dsh-memory: actual Fernet writer, but it postdates xz ----------------------------------------------------- https://github.com/boomzikazita/dsh-memory https://github.com/boomzikazita/dsh-memory/blob/main/scripts/vault.py GitHub creation: August 18, 2026, after the captured July 10-20 stream. Chinese README documents memory recall, proposed writes requiring confirmation, session harvesting, and a VAULT.md.enc that can be synchronized with Git while the key is excluded. Unlike an earlier README-only candidate, the inspected vault.py actually serializes the complete vault as JSON, encrypts it with Fernet, writes a descriptive header plus the token, and atomically replaces the local vault file. The contents were checked against GitHub's size and blob hash. Relevance: a concrete encrypted-state implementation associated with Chinese documentation. Differences: local header-plus-token file, Git backup, no nested outer Base64/chunking or Ubuntu uploader in the inspected files. Creation date also prevents treating this public repo as an established pre-July antecedent. The code was read, not executed; no keys were sought or used. 5. Ouroboros: circulated in China before July, not evidence of Chinese origin --------------------------------------------------------------------------- https://linux.do/t/topic/1660717 https://github.com/razzant/ouroboros Chinese discussion: February 26, 2026. GitHub creation: February 11, 2026. The Chinese post discusses rapid version changes, background reflection and self-modification. The upstream project's current README describes persistent identity, knowledge, reflections and version history. These are owner claims and design descriptions; this review did not authenticate the self-reported evolution history or infer consciousness. Chinese discussion of an external project must not be confused with Chinese authorship. Relevance: rapid releases and background reflection were concepts available in Chinese developer discussions before the xz episode. No cipher/paste link found. 6. Guanxinzhai (观心斋): similar name and overlapping dates, weak link only ----------------------------------------------------------------------- https://forum.trae.cn/t/topic/114058 https://www.cloudyu.store/ Forum date: July 12, 2026. Caption text lists development on July 10-12. The author introduces a TRAE competition demo for personalized rational decision advice, questionnaires, cognitive-bias recognition and decision review. The public homepage still identifies itself as Guanxinzhai / GXhaven and offers questions about jobs, relationships and procrastination. This is not the exact name xinzhai, and its demonstrated purpose differs from an autonomous swarm. Relevance: worth retaining as a name-plus-time candidate, not as attribution. Targeted searches for its name with encryption/xinzhai and its domain with GitHub produced no verified technical join. The forum post and public homepage were inspected; no login, API submission, private profile or user data accessed. No xz labels, matching payloads, cryptography or Ubuntu posting mechanism found. Do not infer common operator from name and date alone. 7. Hermes Agent 笔记: a public Chinese-language operational notebook ----------------------------------------------------------------- https://test-github-repo.vercel.app/ https://test-github-repo.vercel.app/posts-manifest.js Search results exposed a small public notebook. The directly opened HTML has an empty initial list; its linked public manifest contains metadata for 32 posts and declares generation August 11, 2026. This was retrieved as text, not run. Metadata describes multi-agent decision protocols, scheduled operations, and a July 21 migration of three OpenClaw workers from a Mac to an Ubuntu server. Relevance: a new public surface with concrete Chinese-language agent-operation notes and dated summaries, beyond generic tutorials. The page describes notes intended to be copied to another agent. Publication dates are self-declared, not independently archived; metadata is not proof the operations occurred. No xinzhai, xz_knowledge, Ubuntu paste hostname or Fernet occurs in the manifest. Article bodies and full operational configurations were not inspected here. What this adds to the investigation ---------------------------------- There is no need to assume the motivating idea is absent from Chinese discourse: creator posts discuss persistent memory, continual operation and agent teams. The strongest specific implementation comparison is dsh-memory's encrypted JSON vault, though its date and storage format differ. Golutra is the strongest new creator-described team example. Guanxinzhai is the closest new naming/date lead but currently has no technical connection. The Hermes notebook is a new surface for public operational descriptions, not a counterpart of the opaque stream. These findings do not establish a Chinese lab, escaped agents, an autonomous swarm behind xz, or new learning inside the ciphertext. The existing xz size and cadence evidence still permits an ordinary scheduled state writer. Methods and limits ------------------ Searches covered Chinese terms for persistent memory, self-improvement, heartbeat, encrypted backup, online clipboards and the literal xz identifiers, with targeted LINUX DO, V2EX, Gitee and general-web queries. Translated directory pages were used as discovery leads, followed to creator posts or repositories where possible. No new lead came from the Gitee web-index query; this was not global Gitee code search. Five repository metadata/tree responses were captured; trees were not marked truncated. Four READMEs and one vault source file were decoded and verified by size and Git blob hash. Negative marker checks apply only to those inspected files, not whole repositories. Retrieval dates, URLs and hashes are saved under 122-private/. GitHub repository creation is not necessarily feature creation. LINUX DO pages were readable through the web tool, but direct local HTTP pulls returned 403 and were not retried. V2EX topic 1219367 was a search-only lead after direct web opens failed; its claims are not included as verified findings. No infrastructure was purchased, no messages/posts sent, no fetched code run, no source paste bodies added to the public export, and no ciphertext decrypted.