Operator Memory — Development skill for Claude Code

Operator Memory

The self-improving context engine for coding agents.

Agents excel in a session but forget everything the moment it ends. Future sessions waste tokens re-gathering an incomplete context: re-exploring the codebase, re-learning the architecture, re-teaching decisions and corrections.

Operator Memory gives the agent a brain for documenting all their work. As the agent works, it automatically documents within this brain — specs, decisions, standards, research, lessons. Every new session starts from those files.

What You Get

• A Complete Context Engine — Operator Memory provides memory, documentation, codebase indexes, and skills within a single integrated system.
• Automatic Documentation — Specs, decisions, research, and lessons are automatically documented by the agent during normal work. No capture step. No background tasks.
• Transparent Memory — Memory is stored as documents you can read, update, and delete.
• Sharable Knowledge — Every document is optionally shareable. Track documents with Git and share knowledge with your team.
• Zero Infrastructure — No embeddings, no vector database, no background pipelines, no model configuration.

How It Works

Operator gives the agent a durable workspace of Markdown, kept in three places:

• .operator/ — private project knowledge, stays on your machine
• .operator-shared/ — project knowledge published with the repository
• ~/.operator/user/ — your personal rules and knowledge, used across projects

Every session runs the same loop:

1. Consult — the agent starts from your Brain: instructions, codebase index, specs, guides.
2. Build — the agent does normal development work, informed by that knowledge.
3. Update — the agent records what changed: new specs, decisions, standards, lessons.

When project truth changes, the agent updates the