Skip to main content

Profiles: Running Multiple Agents

Run multiple independent Subnaut agents on the same machine — each with its own config, API keys, memory, sessions, skills, and gateway state.

What are profiles?

A profile is a separate Subnaut home directory. Each profile gets its own directory containing its own config.yaml, .env, SOUL.md, memories, sessions, skills, cron jobs, and state database. Profiles let you run separate agents for different purposes — a coding assistant, a personal bot, a research agent — without mixing up Subnaut state.

Give every agent its own profile

Never point two agent processes at the same profile (the same Subnaut home). Both write memory automatically, and each loads the other's writes into its system prompt at session start — so two writers on one home compound each other's state until it stops being anything you configured. Profiles exist exactly to prevent this; agents that need shared memory should use an external memory provider instead.

When you create a profile, it automatically becomes its own command. Create a profile called coder and you immediately have coder chat, coder setup, coder gateway start, etc.

Quick start

subnaut profile create coder # creates profile + "coder" command alias
coder setup # configure API keys and model
coder chat # start chatting

That's it. coder is now its own Subnaut profile with its own config, memory, and state.

Creating a profile

tip

Quickest setup: run subnaut setup --portal inside the new profile to wire up models + tools at once. See Nous Portal.

Blank profile

subnaut profile create mybot

Creates a fresh profile with bundled skills seeded. Run mybot setup to configure API keys, model, and gateway tokens.

If you plan to use this profile as a kanban worker (or want the kanban orchestrator to route work to it), pass --description "<role>" at create time so the orchestrator knows what it's good at:

subnaut profile create researcher --description "Reads source code and external docs, writes findings."

You can also set or auto-generate the description later with subnaut profile describe — see the Kanban guide for the full routing model.

Clone config only (--clone)

subnaut profile create work --clone

Copies your current profile's config.yaml, .env, SOUL.md, and skills into the new profile. Same API keys, model, and capabilities, but fresh sessions and memory. Edit ~/.subnaut/profiles/work/.env for different API keys, or ~/.subnaut/profiles/work/SOUL.md for a different personality.

Clone everything (--clone-all)

subnaut profile create backup --clone-all

Copies everything — config, API keys, personality, all memories, skills, cron jobs, plugins. A complete working snapshot. Per-profile history is excluded (session history, state.db, backups/, state-snapshots/, checkpoints/) — these belong to the source profile and can reach tens of GB. For a full backup including history, use subnaut profile export or subnaut backup instead.

OAuth logins are shared, not copied

Anthropic (Claude Pro/Max), OpenAI Codex, and xAI OAuth logins use single-use refresh tokens — a copy of one is not a second credential, it is the same credential with two owners, and the first profile to refresh it revokes it for every other copy. --clone-all (and the backend's profile-creation credential mirroring) therefore drops those OAuth rows from the clone. The new profile keeps reading the login from the root ~/.subnaut/auth.json, and a token refresh performed inside any profile is written back to root, so all profiles stay signed in. Static API keys are copied as usual. To give a profile its own separate OAuth login, run subnaut -p <name> auth add <provider> inside it.

Clone from a specific profile

subnaut profile create work --clone-from coder

--clone-from <source> selects the source profile directly and implies a config/skills/SOUL clone. Combine it with --clone-all when you want a full copy of that source profile:

subnaut profile create work-backup --clone-from coder --clone-all
Honcho memory + profiles

When Honcho is enabled, clone operations automatically create a dedicated AI peer for the new profile while sharing the same user workspace. Each profile builds its own observations and identity. See Honcho -- Multi-agent / Profiles for details.

Using profiles

Command aliases

Every profile automatically gets a command alias at ~/.local/bin/<name>:

coder chat # chat with the coder agent
coder setup # configure coder's settings
coder gateway start # start coder's gateway
coder doctor # check coder's health
coder skills list # list coder's skills
coder config set model.default anthropic/claude-sonnet-4

The alias works with every subnaut subcommand — it's just subnaut -p <name> under the hood.

The -p flag

You can also target a profile explicitly with any command:

subnaut -p coder chat
subnaut --profile=coder doctor
subnaut chat -p coder -q "hello" # works in any position

Sticky default (subnaut profile use)

subnaut profile use coder
subnaut chat # now targets coder
subnaut tools # configures coder's tools
subnaut profile use default # switch back

Sets a default so plain subnaut commands target that profile. Like kubectl config use-context.

Knowing where you are

The CLI always shows which profile is active:

  • Prompt: coder ❯ instead of
  • Banner: Shows Profile: coder on startup
  • subnaut profile: Shows current profile name, path, model, gateway status

Profiles vs workspaces vs sandboxing

Profiles are often confused with workspaces or sandboxes, but they are different things:

  • A profile gives Subnaut its own state directory: config.yaml, .env, SOUL.md, sessions, memory, logs, cron jobs, and gateway state.
  • A workspace or working directory is where terminal commands start. That is controlled separately by terminal.cwd.
  • A sandbox is what limits filesystem access. Profiles do not sandbox the agent.

On the default local terminal backend, the agent still has the same filesystem access as your user account. A profile does not stop it from accessing folders outside the profile directory.

If you want a profile to start in a specific project folder, set an explicit absolute terminal.cwd in that profile's config.yaml:

terminal:
backend: local
cwd: /absolute/path/to/project

Using cwd: "." on the local backend means "the directory Subnaut was launched from", not "the profile directory".

Also note:

  • SOUL.md can guide the model, but it does not enforce a workspace boundary.
  • Changes to SOUL.md take effect cleanly on a new session. Existing sessions may still be using the old prompt state.
  • Asking the model "what directory are you in?" is not a reliable isolation test. If you need a predictable starting directory for tools, set terminal.cwd explicitly.

Running gateways

Each profile runs its own gateway as a separate process with its own bot token:

coder gateway start # starts coder's gateway
assistant gateway start # starts assistant's gateway (separate process)

Different bot tokens

Each profile has its own .env file. Configure a different Telegram/Discord/Slack bot token in each:

# Edit coder's tokens
nano ~/.subnaut/profiles/coder/.env

# Edit assistant's tokens
nano ~/.subnaut/profiles/assistant/.env

Safety: token locks

If two profiles accidentally use the same bot token, the second gateway will be blocked with a clear error naming the conflicting profile. Supported for Telegram, Discord, Slack, WhatsApp, and Signal.

Persistent services

coder gateway install # creates subnaut-gateway-coder systemd/launchd service
assistant gateway install # creates subnaut-gateway-assistant service

Each profile gets its own service name. They run independently.

Inside the official Docker image

Per-profile gateways are supervised by s6-overlay (PID 1 in the container), so subnaut profile create <name> automatically registers an s6 service slot at /run/service/gateway-<name>/. subnaut -p <name> gateway start/stop/restart dispatches to s6-svc instead of spawning a bare process — crashes are auto-restarted and docker restart preserves the previously-running set of gateways. See Per-profile gateway supervision for details.

Configuring profiles

Each profile has its own:

  • config.yaml — model, provider, toolsets, all settings
  • .env — API keys, bot tokens
  • SOUL.md — personality and instructions
coder config set model.default anthropic/claude-sonnet-4
echo "You are a focused coding assistant." > ~/.subnaut/profiles/coder/SOUL.md

If you want this profile to work in a specific project by default, also set its own terminal.cwd:

coder config set terminal.cwd /absolute/path/to/project

From the desktop app

Subnaut Desktop manages every profile from one window. The profile rail switches which profile you're working in, and the Applies to selector on the config-backed settings pages edits another profile's settings without switching the whole app — see Per-profile settings.

Updating

subnaut update pulls code once (shared) and syncs new bundled skills to all profiles automatically:

subnaut update
# → Code updated (12 commits)
# → Skills synced: default (up to date), coder (+2 new), assistant (+2 new)

User-modified skills are never overwritten.

Managing profiles

subnaut profile list # show all profiles with status
subnaut profile show coder # detailed info for one profile
subnaut profile rename coder dev-bot # rename (updates alias + service)
subnaut profile export coder # pack into coder.tar.gz (shareable; keys stripped)
subnaut profile import coder.tar.gz # install an archive as a new profile

In chat, the same two live as /export and /import — and in the desktop app as ⌘K → Export/Import profile…. See Sharing a profile.

Naming the default profile

The default profile's internal ID is always default — it can't be truly renamed because ~/.subnaut is the installation root. Renaming it instead sets a display name, which UI surfaces show in place of the bare ID:

subnaut profile rename default Harumesu # Unicode fine: 小助手

The display name appears in subnaut profile list/show, the /profile chat command, and the desktop app (including the Bot Mode roster). It is presentation-only: -p default, service names, cron jobs, and every other reference keep using the canonical default ID. It is stored as display_name in ~/.subnaut/profile.yaml; remove that line to revert. Named profiles can carry a display_name too (it survives a real rename), but rename for them still renames the profile itself.

Deleting a profile

subnaut profile delete coder

This stops the gateway, removes the systemd/launchd service, removes the command alias, and deletes all profile data. You'll be asked to type the profile name to confirm.

Use --yes to skip confirmation: subnaut profile delete coder --yes

note

You cannot delete the default profile (~/.subnaut). To remove everything, use subnaut uninstall.

Tab completion

# Bash
eval "$(subnaut completion bash)"

# Zsh
eval "$(subnaut completion zsh)"

Add the line to your ~/.bashrc or ~/.zshrc for persistent completion. Completes profile names after -p, profile subcommands, and top-level commands.

How it works

Profiles use the SUBNAUT_HOME environment variable. When you run coder chat, the wrapper script sets SUBNAUT_HOME=~/.subnaut/profiles/coder before launching subnaut. Since 119+ files in the codebase resolve paths via get_subnaut_home(), Subnaut state automatically scopes to the profile's directory — config, sessions, memory, skills, state database, gateway PID, logs, and cron jobs.

This is separate from terminal working directory. Tool execution starts from terminal.cwd (or the launch directory when cwd: "." on the local backend), not automatically from SUBNAUT_HOME.

On host installs, tool subprocesses keep your real OS-user HOME by default so existing CLI credentials under ~ keep working across profiles. Profile data is isolated by SUBNAUT_HOME, not by changing HOME. Container backends still use {SUBNAUT_HOME}/home for persistent tool state, and host users who need strict per-profile tool config can opt in with terminal.home_mode: profile.

This means two things that are easy to mix up:

  • SUBNAUT_HOME is the profile boundary. It controls Subnaut config, .env, memory, sessions, skills, logs, cron jobs, gateway state, and other Subnaut data.
  • HOME is the operating-system/user home that external CLIs expect. On host installs, Subnaut keeps it as the real user home by default so tools like git, ssh, gh, az, npm, Claude Code, and Codex find the same credentials they use in your normal shell.

The tradeoff is that host profiles share normal user-level CLI state by default. If you need separate CLI identities per profile, set terminal.home_mode: profile in that profile's config.yaml. In that mode Subnaut launches tool subprocesses with HOME={SUBNAUT_HOME}/home; you then need to initialize or link the profile-specific ~/.ssh, ~/.gitconfig, ~/.config/gh, cloud CLI auth, Claude/Codex auth, npm state, and similar files inside that profile home.

Subnaut also exposes SUBNAUT_REAL_HOME to subprocesses so scripts can still find the actual account home when home_mode: profile is active.

The default profile is simply ~/.subnaut itself. No migration needed — existing installs work identically.

Sharing a profile

A profile you built on one machine can go to another — your own workstation, a teammate's laptop, or the community. Two paths:

Send a file. /export packs the profile into one .tar.gz — skills, memory, persona, crons, plugins, settings, and (from the desktop) your theme and layout. API keys are stripped. The recipient runs /import.

# In chat, run /export, hand over the file, and they run /import on it
subnaut profile export coder
subnaut profile import ./coder.tar.gz --name coder

Publish a distribution. Package the profile as a git repository so recipients install it with one command and pull versioned updates later. Carries the SOUL, config, skills, cron jobs, and MCP connections; credentials, memories, and sessions stay per-machine.

# Install a whole agent from a git repo
subnaut profile install github.com/you/research-bot --alias

# Update later when the author ships a new version (keeps your memories + .env)
subnaut profile update research-bot

Use an export file for a one-time handoff or a move; use a distribution for an agent you'll keep shipping. See Profile Distributions: Share a Whole Agent for both — the comparison table, authoring, publishing, update semantics, and the security model.