Claude Code Memory: CLAUDE.md, /memory, and MCP Context

Claude Code already has memory. The official memory path combines CLAUDE.md files you write, auto memory Claude writes from corrections and preferences, and the /memory command for viewing and editing what is loaded.

Origin is for the next problem: keeping evolving work context local, source-backed, and available outside one Claude Code session or one Claude-only surface.

Each Claude Code session starts with a fresh context window. Claude Code carries knowledge forward through CLAUDE.md files and auto memory, and both are loaded into new conversations as context.

That makes Claude Code memory useful for persistent instructions. It also means memory competes with the rest of the context window, so it should stay concise and scoped.

CLAUDE.md is excellent for project-level instructions: build commands, test commands, architecture notes, coding standards, and long-lived conventions the whole team should share.

It should not become a dumping ground for every transient observation from every coding session. When the file gets too large or contradictory, Claude has more context to scan and less room for the current task.

If Claude Code seems to forget something, first inspect the built-in memory surface. /memory is the place to view and edit what Claude Code has loaded.

That step matters because some problems are not Origin problems. The memory may be missing, stale, too broad, duplicated, or loaded at the wrong scope.

Use Origin when project context needs provenance, review, deletion, handoff, distillation, and access from more than one MCP-compatible tool.

Useful Origin captures are specific and grounded: why a decision was made, what tradeoffs were considered, what command verifies a change, which module owns a behavior, or what gotcha should not be rediscovered next week.

The Claude Code plugin is the most complete Origin path because it adds /init, /brief, /capture, /recall, /handoff, /distill, and review workflows around the local daemon and MCP connector.

After installing, restart Claude Code if prompted, run /init once, then verify a harmless capture and recall before relying on Origin for real project memory.

Origin exposes memory through its MCP server. Claude Code can write what it learns and recall relevant project context later. The same work context can also be available to Cursor, Codex, Claude Desktop, Gemini CLI, and other MCP clients when configured.

That makes Origin a shared local layer for AI-assisted development rather than a single-client note file.