HiClaw user deployment: matching chat and container screenshots Reviewed September 6, 2026 UTC. Public read-only evidence. PRIMARY OPERATOR POST https://linux.do/t/topic/1700242/6 Thread https://linux.do/t/topic/1700242 was readable through the web search reader. Mars-KK's March8,2026 post describes roughly a week using HiClaw, multiple workers, shared MinIO files, automatic groups and mutual mentions. Another participant reports quickly exhausting a Qwen-labelled token allowance; that anecdote is not billing or model-identity verification. No full thread archive was obtained by direct requests: the separate two-page capture process stalled and was interrupted after repeated live-handle polls. The blog review queued second in that process remains unverified in this pass. TWO ORIGINAL IMAGES RETRIEVED AND VISUALLY INSPECTED https://cdn3.ldstatic.com/original/4X/5/7/0/5703415d77befaf7ca487b2af432649344e4256e.png HTTP200,438,218 bytes. A Matrix-style chat shows a stock-analysis team, a23:26 group-creation announcement, stock-alpha, stock-beta and data-harvest roles, and instructions for mentions and collaboration. The sidebar additionally shows frontend-dev and a manager. It proposes cross-checking between the two analysts and data support from the collector. These are setup instructions, not the actual analysis exchange. The screenshot also has truncated keepalive/sync/status previews that cannot establish completion or duration. https://cdn3.ldstatic.com/original/4X/c/d/e/cde3725be8aab606367a6f9fa77a9aa473c847c3.png HTTP200,182,646 bytes. A container UI shows five visible named rows: hiclaw-worker-frontend-dev, hiclaw-worker-data-harvest, hiclaw-worker-stock-beta, hiclaw-worker-stock-alpha and hiclaw-manager, each marked started. Its header counts seven total/seven started, but only five rows are visible, so seven must not be reported as seven agents. The displayed addresses are private container-network addresses, not public egress or Chinese hosting evidence. EVIDENCE JOIN AND LIMITS The repeated worker names tie the two images to a consistent displayed setup: four worker names and a manager, with a stock-team room. This is a useful voluntary operator deployment report, stronger than an illustrative README transcript. It does not authenticate the underlying model calls, prove screenshot timestamps, demonstrate unattended operation, or establish completed stock analysis/trades. Do not follow the displayed local server addresses or attempt to enter the operator's rooms. No public room URL or exported message history was provided in the inspected post. RELATED LEADS https://jjbiji.com/blogs/hiclaw-worker-market-review/ Search-indexed author review describes template-market friction and a documentation-worker experiment. Web-reader fetch failed; direct capture did not finish. No claims from its unseen remainder are accepted here. https://github.com/agentscope-ai/AgentTeams/issues/422 Search surfaced a HiClaw remote-access deployment issue. It is a potential repository/operator-history route, not yet directly inspected in this report. The current AgentTeams namespace and earlier HiClaw naming need checking before attribution. ASSESSMENT Chinese-language independent user evidence for an intentionally deployed agent team; no escaped-swarm or XZ connection established. The main missing artifact is a sequential message export with task/result references. Continue through public deployment issues and voluntarily redacted debug attachments, avoiding configuration dumps or credentials. Existing server successfully retrieved the image CDN; additional infrastructure was not required for these screenshots. PRESERVATION 316-private/screenshot-0.png and screenshot-1.png, capture-status.json, SHA256SUMS and publication-check.json. Raw images remain private; report links original public sources. No installation, model request, login, messaging, trading or target execution.