Manage OpenClaw Sessions and Multi-Agent Workflows

Ever felt like your AI bot is losing its mind after a long conversation? Or maybe you’re trying to figure out how to manage a dozen different chat threads without everything turning into a giant mess. Managing sessions and multi-user setups can be a headache when you just want things to work.

How do I start a fresh conversation?

If you want to clear the slate, just send /new or /reset as a standalone message. It is the quickest way to get a clean start.

Do sessions reset automatically if I never send /new?

Yes. Sessions expire after session.idleMinutes, which defaults to 60. The next message you send starts a fresh session id for that chat key. This does not delete your transcripts—it just starts a new session.

{
  session: { idleMinutes: 240 }
}

Is there a way to make a team of OpenClaw instances (one CEO and many agents)?

Yes, you can do this via multi-agent routing and sub-agents. You can create one coordinator agent and several worker agents with their own workspaces and models.

That said, this is best seen as a fun experiment. It is token heavy and often less efficient than using one bot with separate sessions.

Why did context get truncated mid-task? How do I prevent it?

Session context is limited by the model window. Long chats, large tool outputs, or many files can trigger compaction or truncation.

What helps:

• Ask the bot to summarize the current state and write it to a file
• Use /compact before long tasks, and /new when switching topics
• Keep important context in the workspace and ask the bot to read it back
• Use sub-agents for long or parallel work
• Pick a model with a larger context window

How do I completely reset OpenClaw but keep it installed?

If you need a total wipe without uninstalling, run this:

openclaw reset

For a non-interactive full reset, use:

openclaw reset --scope full --yes --non-interactive

Then you can re-run the onboarding process:

openclaw onboard --install-daemon

I’m getting “context too large” errors—how do I reset or compact?

When the context gets too heavy, you have two main options.

Compact (keeps the conversation but summarizes older turns):

/compact

Reset (fresh session ID for the same chat key):

/new
/reset

If it keeps happening:

• Enable or tune session pruning (agents.defaults.contextPruning)
• Use a model with a larger context window

Why am I getting heartbeat messages every 30 minutes?

Heartbeats run every 30m by default. You can tune or disable them in your config:

{
  agents: {
    defaults: {
      heart

```json
{
  agents: {
    defaults: {
      heartbeat: {
        every: "2h"  // or "0m" to disable
      }
    }
  }
}

openclaw logs --follow --json

openclaw directory groups list --channel whatsapp