Two Claude Code accounts.
One AgentsRoom. Zero shell tricks.

There is no hard limit. Each account is a directory on disk. Add a Work account, a Personal account, one account per client, a test account: AgentsRoom lists them all in the Settings panel and lets you pick any of them per project or per agent.

No. AgentsRoom drives Claude Code's CLAUDE_CONFIG_DIR mechanism directly. No external switcher, no shell wrapper, no extra dependency. The sign-in flow is fully embedded in the Settings panel.

Yes. When you add an account in AgentsRoom, click "Custom path" and point at your existing CCS profile directory, for example ~/.ccs/instances/work. AgentsRoom reuses the credentials already saved there. No re-login required.

Yes. The project pins a default account, but each agent can override it. Open a project pinned on the Work account, edit one specific agent to use the Personal account, and the two agents run in parallel on different Claude accounts in the same window.

Yes. AgentsRoom scans every configured account directory, plus ~/.claude as the fallback, when reading session metadata. PIDs are globally unique so each agent's session metafile is found in exactly one directory. Per-session token counts, cache hit rate and per-agent file diffs work identically across accounts.

Nothing breaks. The agents fall back to the default Claude account silently. The deleted directory is left on disk in case you want to point another profile at it later. You can rebind the orphaned agents to another account at any time from the Edit Agent dialog.

No. Each account directory stays on your local machine. AgentsRoom never reads, copies or transmits credentials. The sign-in flow runs the official claude CLI in a local PTY, OAuth happens between Anthropic and your browser as usual.

When an agent's account changes, its previous session lives under the old account directory and cannot be resumed under the new one. AgentsRoom detects the failure and starts a fresh session automatically. No manual cleanup needed.

Each Claude account keeps its own quota and its own rate limits: separate accounts never share or throttle each other, so a heavy agent run on one account leaves the other untouched. Whether running several paid subscriptions fits your situation depends on Anthropic's terms of service for your account type. AgentsRoom simply manages the sign-ins and keeps each account's identity isolated on disk.

Yes. Sidebar folders carry their own defaults, and the Claude account is one of them. Pin Work on the folder holding your work repositories and every project inside starts on that account, including projects added later and projects in sub-folders. The resolution order is: agent override, project pin, nearest folder that pins an account, global default, then ~/.claude.

The one you are actually spending, resolved separately for each provider: the account of the agent in the foreground first, otherwise the account this project would launch on, otherwise your primary account. The gauge tooltip names it, and the usage popover lists one section per signed-in account, so a work quota and a personal quota are never added into a single figure.

Yes, with the quota breakdown enabled in the beta panel. AgentsRoom takes the percentage published by the account for the running window and splits it across your projects and agents, weighted by the local cost of each session. It is an estimate and it is marked as such: consumption AgentsRoom cannot see, from another computer or from claude.ai, is missing from the calculation, so this is never an invoice.

Yes, once you turn on "Use my personal CLI configuration" in Settings. Signing an account in gives it its own Claude Code configuration directory, and Claude Code loads its whole user layer from there: without that switch a new account starts empty, so your own slash commands, skills, subagents, CLAUDE.md, hooks, plugins and user-scope MCP servers are not loaded. The switch links them into every account at once and keeps them up to date, while credentials, sessions, transcripts and usage stay isolated per account. AgentsRoom also lists exactly what it found in your configuration, so you never have to guess whether something is being used.

Yes, that is exactly what this feature does. Each Claude account you add gets its own Claude Code configuration directory, and every agent is launched with the account you picked for its project. A work agent and a personal agent then run side by side, in the same window, each signed in to its own account, with no logout in between. The limit you may have hit is in the Claude web app, which keeps one login per browser profile; the command line has no such limit once each account has its own directory.

No. As of this writing, Anthropic offers no way to merge two Claude accounts: each one keeps its own subscription, conversation history and quota. What AgentsRoom does is the opposite, and it needs no merge: keep both accounts, sign each of them in once, pin one per project or per agent, and use them from the same app. You get what people usually want from a merge, one place for everything, while the two accounts and their quotas stay separate.