> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# agents

# `openclaw agents`

Manage isolated agents (workspaces + auth + routing).

Related:

* Multi-agent routing: [Multi-Agent Routing](/concepts/multi-agent)
* Agent workspace: [Agent workspace](/concepts/agent-workspace)

## Examples

```bash theme={"dark"}
openclaw agents list
openclaw agents add work --workspace ~/.openclaw/workspace-work
openclaw agents bindings
openclaw agents bind --agent work --bind telegram:ops
openclaw agents unbind --agent work --bind telegram:ops
openclaw agents set-identity --workspace ~/.openclaw/workspace --from-identity
openclaw agents set-identity --agent main --avatar avatars/openclaw.png
openclaw agents delete work
```

## Routing bindings

Use routing bindings to pin inbound channel traffic to a specific agent.

List bindings:

```bash theme={"dark"}
openclaw agents bindings
openclaw agents bindings --agent work
openclaw agents bindings --json
```

Add bindings:

```bash theme={"dark"}
openclaw agents bind --agent work --bind telegram:ops --bind discord:guild-a
```

If you omit `accountId` (`--bind <channel>`), OpenClaw resolves it from channel defaults and plugin setup hooks when available.

### Binding scope behavior

* A binding without `accountId` matches the channel default account only.
* `accountId: "*"` is the channel-wide fallback (all accounts) and is less specific than an explicit account binding.
* If the same agent already has a matching channel binding without `accountId`, and you later bind with an explicit or resolved `accountId`, OpenClaw upgrades that existing binding in place instead of adding a duplicate.

Example:

```bash theme={"dark"}
# initial channel-only binding
openclaw agents bind --agent work --bind telegram

# later upgrade to account-scoped binding
openclaw agents bind --agent work --bind telegram:ops
```

After the upgrade, routing for that binding is scoped to `telegram:ops`. If you also want default-account routing, add it explicitly (for example `--bind telegram:default`).

Remove bindings:

```bash theme={"dark"}
openclaw agents unbind --agent work --bind telegram:ops
openclaw agents unbind --agent work --all
```

## Identity files

Each agent workspace can include an `IDENTITY.md` at the workspace root:

* Example path: `~/.openclaw/workspace/IDENTITY.md`
* `set-identity --from-identity` reads from the workspace root (or an explicit `--identity-file`)

Avatar paths resolve relative to the workspace root.

## Set identity

`set-identity` writes fields into `agents.list[].identity`:

* `name`
* `theme`
* `emoji`
* `avatar` (workspace-relative path, http(s) URL, or data URI)

Load from `IDENTITY.md`:

```bash theme={"dark"}
openclaw agents set-identity --workspace ~/.openclaw/workspace --from-identity
```

Override fields explicitly:

```bash theme={"dark"}
openclaw agents set-identity --agent main --name "OpenClaw" --emoji "🦞" --avatar avatars/openclaw.png
```

Config sample:

```json5 theme={"dark"}
{
  agents: {
    list: [
      {
        id: "main",
        identity: {
          name: "OpenClaw",
          theme: "space lobster",
          emoji: "🦞",
          avatar: "avatars/openclaw.png",
        },
      },
    ],
  },
}
```

## Session Journal

Agents can write a reflective LLM journal entry each time a session resets via `/new` or `/reset`.
Opt in per agent with `sessionJournal.enabled: true`.

```json5 theme={"dark"}
{
  agents: {
    list: [
      {
        id: "claire",
        sessionJournal: {
          enabled: true,
          // optional — include {transcript} where session text should be injected
          prompt: "Write structured patient notes in SOAP format.\n\nSession transcript:\n{transcript}",
        },
      },
    ],
  },
}
```

| Field     | Type      | Default  | Description                                                                                                                           |
| --------- | --------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------- |
| `enabled` | `boolean` | `false`  | Enable journal generation for this agent                                                                                              |
| `prompt`  | `string`  | built-in | LLM prompt. Include `{transcript}` where the session text should be injected; if absent, the transcript is appended after the prompt. |

Journal files are written to `<effectiveWorkspaceDir>/journal/YYYY-MM-DD-HHMMss-<slug>.md`. In multi-user
mode (workspace lanes), each lane gets its own `journal/` folder — journals are isolated per
user, not shared with other lanes on the same agent.

The bundled `session-journal` hook must be enabled for this config to take effect:

```bash theme={"dark"}
wednesdayai hooks enable session-journal
```

See [Hooks: session-journal](/automation/hooks#session-journal) for full details.