06ae605051
Address findings from pedagogical review simulating a non-expert user: - Add CLAUDE.md to project root (was referenced but missing) - Fix README score from 12/9/1 to 13/8/1 (match feature-map.md) - Add Expected Output sections to examples 01, 02, 05, 09, 10 - Create pipeline-output/ and briefings/ directories - Add example ordering guidance in README - Add plan requirements for examples 11/13 in prerequisites - Add skill frontmatter explanation in GETTING-STARTED.md - Explain Cowork/Dispatch with links in cowork-integration - Expand .gitignore with node_modules and generated output files - Add model override hints in agent frontmatter comments Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
87 lines
2.7 KiB
Markdown
87 lines
2.7 KiB
Markdown
# Example 05: Memory System
|
|
|
|
**Capability:** Claude Code maintains persistent memory across sessions through a
|
|
hierarchy of markdown files. What is written in one session is available in the next.
|
|
|
|
**OpenClaw equivalent:** Daily markdown logs + MEMORY.md + vector search (SQLite-vec).
|
|
|
|
---
|
|
|
|
## How the Hierarchy Works
|
|
|
|
Claude Code loads context in this order, from broadest to narrowest:
|
|
|
|
1. `~/.claude/CLAUDE.md` - global preferences, always loaded
|
|
2. `CLAUDE.md` in the project root - project-specific config, always loaded
|
|
3. `memory/MEMORY.md` - session state, loaded if referenced in CLAUDE.md
|
|
4. `.claude/` managed memory - auto-updated by Claude when `--memory` is active
|
|
|
|
The file loaded earlier provides the frame. Later files narrow it.
|
|
|
|
---
|
|
|
|
## The Prompt
|
|
|
|
```
|
|
Read this project's CLAUDE.md and summarize what you learn about the project
|
|
in three bullet points.
|
|
|
|
Then create a file at memory/project-notes.md with:
|
|
- Today's date as a header
|
|
- The three-bullet summary
|
|
- A note that says "Memory system demonstrated successfully"
|
|
|
|
Finally, explain in one paragraph how this file will be available in the
|
|
next Claude Code session without re-reading CLAUDE.md.
|
|
```
|
|
|
|
---
|
|
|
|
## What Happens
|
|
|
|
Claude Code will:
|
|
|
|
1. Use Read to load `CLAUDE.md` from the project root
|
|
2. Synthesize the project context into three bullets
|
|
3. Use Write to create `memory/project-notes.md`
|
|
4. Explain how CLAUDE.md references cause files to be auto-loaded
|
|
|
|
---
|
|
|
|
## Expected Output
|
|
|
|
Claude creates `memory/project-notes.md` and then explains how memory works.
|
|
The file will look like:
|
|
|
|
```markdown
|
|
# March 26, 2026
|
|
|
|
- This is a companion repo comparing OpenClaw and Claude Code capabilities
|
|
- It contains 13 examples, agents, skills, hooks, and documentation
|
|
- The project maps 22 OpenClaw features to Claude Code equivalents
|
|
|
|
Memory system demonstrated successfully.
|
|
```
|
|
|
|
Claude will then explain something like:
|
|
|
|
> "This file is inside the `memory/` directory, which is referenced in
|
|
> CLAUDE.md. Because Claude Code loads CLAUDE.md at every session start,
|
|
> and CLAUDE.md mentions the memory directory, files here persist across
|
|
> sessions without any extra setup."
|
|
|
|
**How you know it worked:**
|
|
- `memory/project-notes.md` exists and contains today's date
|
|
- The three bullets accurately summarize what CLAUDE.md says
|
|
- Claude's explanation mentions the CLAUDE.md hierarchy
|
|
|
|
---
|
|
|
|
## Why This Matters
|
|
|
|
OpenClaw uses SQLite-vec for semantic memory search across sessions. Claude Code
|
|
uses structured markdown with explicit file references. Both achieve persistence.
|
|
The markdown approach is more inspectable: you can read, edit, and version control
|
|
every piece of memory Claude has about your project.
|
|
|
|
The `memory/MEMORY.md` file in this repo shows the pattern at scale.
|