Agent workspace

The workspace is the agent’s home: the working directory used for file tools and workspace context. Keep it private and treat it as memory.

This is separate from ~/.openclaw/, which stores config, credentials, and sessions.

The workspace is the default cwd, not a hard sandbox. Tools resolve relative paths against the workspace, but absolute paths can still reach elsewhere on the host unless sandboxing is enabled. If you need isolation, use agents.defaults.sandbox (and/or per-agent sandbox config).

When sandboxing is enabled and workspaceAccess is not "rw", tools operate inside a sandbox workspace under ~/.openclaw/sandboxes, not your host workspace.

Default location

• Default: ~/.openclaw/workspace
• If OPENCLAW_PROFILE is set and not "default", the default becomes ~/.openclaw-<profile>/workspace.
• OPENCLAW_WORKSPACE_DIR overrides both of the above when set.
• A non-default OPENCLAW_STATE_DIR keeps the default workspace at <state-dir>/workspace, including scheduled maintenance and the initial main agent entry.
• A sole configured agent inherits the default workspace unless its entry sets workspace.
• In an explicit multi-agent roster, entries without workspace use <agents.defaults.workspace>/<agentId> when that root is configured, or <state-dir>/workspace-<agentId> otherwise. Naming a shared root does not assign it to an agent.

Override in ~/.openclaw/openclaw.json:

{
  agents: {
    defaults: {
      workspace: "~/.openclaw/workspace",
    },
  },
}

Per-agent override: agents.entries.*.workspace. To keep main at an existing shared root in a multi-agent roster, pin agents.entries.main.workspace to that root explicitly; changing agents.defaults.workspace alone sets the base for unpinned entries.

openclaw onboard, openclaw configure, or openclaw setup create the workspace and seed the bootstrap files if they are missing.

Sandbox seed copies only accept regular in-workspace files; symlink/hardlink aliases that resolve outside the source workspace are ignored.

If you already manage the workspace files yourself, disable bootstrap file creation:

{ agents: { defaults: { skipBootstrap: true } } }

Extra workspace folders

Older installs may have created ~/openclaw. Each agent uses one resolved workspace; keeping extra directories does not merge their persona or memory files into the active workspace.

Keep each agent’s workspace path explicit when retaining older directories. Before switching back to an older workspace, stop the Gateway, configure the intended path, run openclaw doctor --fix to migrate retired setup state, and restart. Doctor also discovers legacy setup files in a still-configured agents.defaults.workspace root even when no agent currently uses that root directly. Archive unused folders only after verifying which files you want to retain.

Workspace file map

Standard files OpenClaw expects inside the workspace:

AGENTS.md - operating instructions

Operating instructions for the agent and how it should use memory. Loaded at the start of every session. Good place for rules, priorities, and “how to behave” details.

SOUL.md - persona and tone

Persona, tone, and boundaries. Loaded every session. Guide: SOUL.md personality guide.

USER.md - directive-based user model (optional)

Stable preferences, communication style, relationships, and active-project context. Write entries as dated active or superseded directives. Loaded every session with a separate 4,000-character budget. See User model.

IDENTITY.md - name, vibe, emoji

The agent’s name, vibe, and emoji. Created/updated during the bootstrap ritual.

AGENTS.md Tools section - local tool conventions

The ## Tools section holds local environment notes and conventions. It does not control tool availability; it is only guidance.

BOOT.md - startup checklist

Optional startup checklist run on Gateway startup when the boot-md hook is enabled. Enabling a different internal hook does not enable boot-md. Keep it short; use the message tool for outbound sends.

BOOTSTRAP.md - first-run ritual

One-time first-run ritual. Only created for a brand-new workspace. Delete it after the ritual is complete.

memory/YYYY-MM-DD.md - daily memory log

Daily memory log (one file per day). Recommended to read today + yesterday on session start.

MEMORY.md - curated long-term memory (optional)

Curated long-term memory: durable non-profile facts, decisions, and short summaries. Keep detailed logs in memory/YYYY-MM-DD.md so memory tools can retrieve them on demand without injecting them into every prompt. Only load MEMORY.md in the main, private session (not shared/group contexts). See Memory for the workflow and automatic memory flush.

skills/ - workspace skills (optional)

Workspace-specific skills. Highest-precedence skill location for that workspace, ahead of project agent skills, personal agent skills, managed skills, bundled skills, and skills.load.extraDirs when names collide.

If a required bootstrap file is missing, OpenClaw injects a “missing file” marker into the session and continues. Optional USER.md and MEMORY.md files are omitted when absent. Large bootstrap files are truncated when injected; adjust general limits with agents.defaults.bootstrapMaxChars (default: 20000) and agents.defaults.bootstrapTotalMaxChars (default: 60000). USER.md keeps its separate 4,000-character cap. openclaw setup can recreate missing defaults without overwriting existing files.

What is NOT in the workspace

These live under ~/.openclaw/ and should NOT be committed to the workspace repo:

• ~/.openclaw/openclaw.json (config)
• ~/.openclaw/state/openclaw.sqlite (shared workspace setup state and attestations)
• ~/.openclaw/agents/<agentId>/agent/openclaw-agent.sqlite (model auth profiles, routing state, standing intents, and other agent-scoped durability)
• ~/.openclaw/agents/<agentId>/agent/openclaw-agent.sqlite (session rows, transcripts, and per-agent runtime state)
• ~/.openclaw/agents/<agentId>/agent/codex-home/ (per-agent Codex runtime account, config, skills, plugins, and native thread state)
• ~/.openclaw/credentials/ (channel/provider state plus legacy OAuth import data)
• ~/.openclaw/agents/<agentId>/sessions/ (legacy migration sources and archive/support artifacts)
• ~/.openclaw/skills/ (managed skills)

If you need to migrate sessions or config, copy them separately and keep them out of version control.

Older OpenClaw releases wrote openclaw-workspace-state.json, .openclaw/workspace-state.json, and .attested workspace sidecars. Current runtime uses only the shared SQLite database for that state. If Doctor reports one of these files, run openclaw doctor --fix; Doctor imports valid legacy state and deletes a source only after verifying the database rows. Empty reserved hashed files under workspace-attestations/ are discarded because they contain no importable state; other unreadable sources stay in place and Doctor names their paths.

Git backup (recommended, private)

Treat the workspace as private memory. Put it in a private git repo so it is backed up and recoverable.

Run these steps on the machine where the Gateway runs (that is where the workspace lives).

1. Initialize the repo

   If git is installed, brand-new workspaces are initialized automatically. If this workspace is not already a repo, run:

   cd ~/.openclaw/workspace
   git init
   git add AGENTS.md SOUL.md IDENTITY.md USER.md memory/
   git commit -m "Add agent workspace"
   
2. Add a private remote

   GitHub web UI

   1. Create a new private repository on GitHub.
   2. Do not initialize with a README (avoids merge conflicts).
   3. Copy the HTTPS remote URL.
   4. Add the remote and push:

   git branch -M main
   git remote add origin <https-url>
   git push -u origin main
   

   GitHub CLI (gh)

   gh auth login
   gh repo create openclaw-workspace --private --source . --remote origin --push
   

   GitLab web UI

   1. Create a new private repository on GitLab.
   2. Do not initialize with a README (avoids merge conflicts).
   3. Copy the HTTPS remote URL.
   4. Add the remote and push:

   git branch -M main
   git remote add origin <https-url>
   git push -u origin main
   
3. Ongoing updates

   git status
   git add .
   git commit -m "Update memory"
   git push
   

Do not commit secrets

Even in a private repo, avoid storing secrets in the workspace:

• API keys, OAuth tokens, passwords, or private credentials.
• Anything under ~/.openclaw/.
• Raw dumps of chats or sensitive attachments.

If you must store sensitive references, use placeholders and keep the real secret elsewhere (password manager, environment variables, or ~/.openclaw/).

Suggested .gitignore starter:

.DS_Store
.env
**/*.key
**/*.pem
**/secrets*

Moving the workspace to a new machine

1. Clone the repo

   Clone the repo to the desired path (default ~/.openclaw/workspace).

2. Update config

   Set agents.entries.<agentId>.workspace to the cloned path in ~/.openclaw/openclaw.json for the agent that should use it. A sole agent without a per-agent override can use agents.defaults.workspace instead; in a multi-agent roster, that setting only changes the base directory for unpinned entries.

3. Verify the workspace

   Run openclaw agents list and confirm that the intended agent points to the cloned path before starting the Gateway. Moving an existing workspace does not require rerunning onboarding.

4. Copy sessions (optional)

   If you need sessions, copy ~/.openclaw/agents/<agentId>/agent/openclaw-agent.sqlite from the old machine separately. Copy ~/.openclaw/agents/<agentId>/sessions/ only when you also need legacy migration inputs or archive/support artifacts.

Advanced notes

• Multi-agent routing can use different workspaces per agent via agents.entries.*.workspace. See Channel routing for routing configuration.
• If agents.defaults.sandbox is enabled, non-main sessions can use per-session sandbox workspaces under agents.defaults.sandbox.workspaceRoot.

Related

• Heartbeat - heartbeat monitors and cron scratch
• Sandboxing - workspace access in sandboxed environments
• Session - session storage paths
• Standing orders - persistent instructions in workspace files