Skip to content

Commit 134b863

Browse files
mkreymanclaude
andcommitted
docs: Add practical workflow example front and center
- Show real-world usage with custom commands and CLAUDE.md - Emphasize human-controlled checkpoint management - Highlight shared memory board feature for parallel sessions - Demonstrate the actual pattern users follow 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
1 parent dda5a7c commit 134b863

File tree

1 file changed

+79
-0
lines changed

1 file changed

+79
-0
lines changed

README.md

Lines changed: 79 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -22,6 +22,85 @@ claude mcp add memory-keeper npx mcp-memory-keeper
2222

2323
That's it! Memory Keeper is now available in all your Claude sessions. Your context is stored in `~/mcp-data/memory-keeper/` and persists across sessions.
2424

25+
## 🚀 Practical Memory Keeper Workflow Example
26+
27+
### **Custom Command + CLAUDE.md = Automatic Context Management**
28+
29+
#### **CLAUDE.md** (condensed example)
30+
31+
```markdown
32+
# Project Configuration
33+
34+
## Development Rules
35+
36+
- Always use memory-keeper to track progress
37+
- Save architectural decisions and test results
38+
- Create checkpoints before context limits
39+
40+
## Quality Standards
41+
42+
- All tests must pass before marking complete
43+
- Document actual vs claimed results
44+
```
45+
46+
#### **Custom Command Example: `/my-dev-workflow`**
47+
48+
```markdown
49+
# My Development Workflow
50+
51+
When working on the provided project:
52+
53+
- Use memory-keeper with channel: <project_name>
54+
- Save progress at every major milestone
55+
- Document all decisions with category: "decision"
56+
- Track implementation status with category: "progress"
57+
- Before claiming anything is complete, save test results
58+
59+
## Workflow Steps
60+
61+
1. Initialize session with project name as channel
62+
2. Save findings during investigation
63+
3. Create checkpoint before major changes
64+
4. Document what actually works vs what should work
65+
```
66+
67+
#### **Usage Example**
68+
69+
```
70+
User: /my-dev-workflow authentication-service
71+
72+
AI: Setting up workflow for authentication-service.
73+
[Uses memory-keeper with channel "authentication-service"]
74+
75+
[... AI works, automatically saving context ...]
76+
77+
User: "Getting close to context limit. Create checkpoint and give me a key"
78+
79+
AI: "Checkpoint created: authentication-service-checkpoint-20250126-143026"
80+
81+
[Continue working until context reset or compact manually]
82+
83+
User: "Restore from key: authentication-service-checkpoint-20250126-143026"
84+
85+
AI: "Restored! Continuing OAuth implementation. We completed the token validation, working on refresh logic..."
86+
```
87+
88+
**The Pattern:**
89+
90+
1. Custom command includes instructions to use memory-keeper
91+
2. AI follows those instructions automatically
92+
3. **When you notice the conversation getting long, YOU ask Claude to save a checkpoint** (like saving your game before a boss fight!)
93+
4. **When Claude runs out of space and starts fresh, YOU tell it to restore using the checkpoint key**
94+
95+
**🎯 Key Feature:** Memory Keeper is a shared board! You can:
96+
97+
- Continue in the same session after reset
98+
- Start a completely new session and restore
99+
- Have multiple Claude sessions running in parallel, all sharing the same memory
100+
- One session can save context that another session retrieves
101+
102+
This enables powerful workflows like having one Claude session doing research while another implements code, both sharing discoveries through Memory Keeper!
103+
25104
## Why MCP Memory Keeper?
26105

27106
Claude Code users often face context loss when the conversation window fills up. This MCP server solves that problem by providing a persistent memory layer for Claude AI. Whether you're working on complex refactoring, multi-file changes, or long debugging sessions, Memory Keeper ensures your Claude assistant remembers important context, decisions, and progress.

0 commit comments

Comments
 (0)