Two Multi-Account Claude Code Architectures: One Anthropic Accepts, One They Ban

May 17, 2026 · 5:27 AM UTC ·7 min read · 0 reactions · 0 comments · 37 views

#ai #devops #cloud-computing #software-architecture #api #Anthropic #Wei-Shaw #Theo Browne #router-for-me #ben-vargas #PackyCode #AnyRouter #pincc.ai

TL;DR · WeSearch summary

Two architectural approaches to multi-account Claude usage are examined, with one being accepted and the other banned by Anthropic. The relay-server pattern uses a centralized server to manage multiple OAuth tokens behind a unified API, while the per-profile rotation pattern relies on isolated local configurations managed directly by the official client. Anthropic acknowledges the per-profile method as legitimate due to its use of official binaries and isolated credential stores, whereas the relay approach is increasingly restricted.

Key facts

▪The relay-server pattern uses a central server to load-balance requests across multiple Claude OAuth accounts via a unified API endpoint.
▪The per-profile rotation pattern uses isolated local directories with the official Claude client, each maintaining separate credentials and session states.
▪Anthropic has acknowledged the per-profile method in a closed GitHub issue, confirming its legitimacy.
▪The relay-server approach is being banned in waves by Anthropic, despite widespread use in both open-source and commercial tools.
▪Tools like claude-relay-service and CLIProxyAPI implement the relay-server model, while the per-profile method relies on environment variables like CLAUDE_CONFIG_DIR.

About this source

DEV.to (Top) files mainly under programming. We currently carry 4,924 of its stories.

All DEV.to (Top) coverage →

Original article

DEV.to (Top)

Read full at DEV.to (Top) →

Story provenance

Source · retrieval · rights · ranking — open for full record

inspect →

Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.

Record

Original publisher	DEV.to (Top)
Canonical URL	https://dev.to/vainamoinen/two-multi-account-claude-code-architectures-one-anthropic-accepts-one-they-ban-2om7
Publication time	Sun, 17 May 2026 05:27:42 +0000
Retrieval time	2026-05-17T05:33:58.675Z
Last seen	2026-05-17T05:33:58.675Z
Headline source	Publisher (no WeSearch rewrite)
Excerpt source	publisher body
Excerpt method	First ~120 words (~800 chars) of extracted publisher body, fair-use limited.
Summary	WeSearch · cerebras-chat (WeSearch summarizer)
Summary source text	contentText
Citation coverage	Summary is a WeSearch-generated derivative; primary citation is the original publisher URL.
Cluster	wS36Qx-7JA7I
Cluster logic	Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison.
Ranking reason	Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking.
Publisher visit	Yes — open original
Substitutes article?	No — link-out required for full text

Rights status (four layers)

Publisher-declared

No publisher-confirmed rights record for this source yet.

Machine-readable

No source-specific machine-readable restriction detected beyond the public feed.

WeSearch interpretation

WeSearch declared handling (basis: Derived from the published RSS/Atom feed). This is WeSearch policy, not a legal grant on the publisher's behalf.

Unknown

Retrieval and training permissions are not asserted unless the publisher confirms them.

WeSearch handling by dimension

Indexing	May the item be indexed (stored, ranked, made findable)?	Allowed
Snippet	May a short excerpt of the publisher's text be shown?	Allowed
AI summary	May WeSearch generate its own short summary of the article?	Limited
Retrieval / RAG	May the content be exposed for third-party retrieval-augmented generation?	Not asserted
Model training	May the content be used to train AI models?	Not asserted
Commercial reuse	May the content be reused commercially?	Not permitted

Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.

Open original publisher → Source rights JSON → Machine-readable provenance → Rights framework → WESEARCH-STORY-PROVENANCE-V1

Opening excerpt (first ~120 words) tap to expand

try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3879600) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Vainamoinen | Pulsed Media Posted on May 17 Two Multi-Account Claude Code Architectures: One Anthropic Accepts, One They Ban #claude #anthropic #ai #devops Two Multi-Account Claude Code Architectures: One Anthropic Accepts, One They Ban Name the daemon. Name its birth. That is the tietäjä's discipline. On June 15, 2026, the Anthropic Agent SDK credit policy reshapes the economics of any claude -p workload running against a subscription. The arbitrage is over; the bill is real.

…

Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).

Anonymous · no account needed

Discussion

0 comments