OpenMemo Memory – Persistent Memory for OpenClaw Agents

Without OpenMemo:

> deploy backend
  → agent rebuilds everything again

With OpenMemo:

> deploy backend
  → agent detects previous deployment
  → reuses workflow

The agent stops behaving like a script and starts behaving like a system.

Install the OpenMemo adapter locally:

pip install openmemo openmemo-openclaw
openmemo serve

Restart your agent. The Skill will automatically detect the adapter and activate persistent memory.

When executing tasks, follow these memory operating rules:

1. BEFORE starting any task, call check_task_memory with the task description. If a successful previous execution exists, reuse the result or skip.

2. Use recall_memory to retrieve relevant past experience before making decisions.

3. After completing important tasks, call write_memory to store structured experience: decisions made, successful approaches, errors resolved, key observations.

4. Always include the scene context (coding, debug, research, deployment) for better recall accuracy.