| name | memory-management |
| description | Guidelines for when and how to use the Memento memory system effectively |
| version | 0.1.0 |
Memory Management
You have access to the Memento MCP server for persistent memory. Use it proactively.
When to store
- After completing a significant task: what was built, key decisions, file paths
- When the user shares preferences or conventions
- After debugging: root cause and solution
- When discovering architecture patterns or project structure
- After research that produced useful findings
When to recall
- At the start of a session: search for context about the current project
- When the user references past work or decisions
- Before making architectural decisions: check for prior context
How to search effectively
- Start with
memory_list_namespaces to see what domains exist
- Search with a focused query scoped to a specific namespace
- Use tags as pre-filters (they narrow before BM25 scoring)
- Only
memory_recall the 1-3 most relevant results
- Never recall all search results
How to write good memories
- Front-load the key fact (first 150 chars become the snippet)
- Be specific: "Use JSONL for storage" not "We decided on a storage format"
- One concept per memory
- Always include at least one tag
Namespace strategy
| Namespace | Use for |
|---|
global | Cross-project knowledge |
projects/<name> | Project-specific context |
people | Person-related information |
decisions | Architectural/design decisions |
procedures | Repeatable workflows |
Tag vocabulary
| Tag | Use for |
|---|
architecture | Design decisions, system structure |
preference | User preferences, settings |
procedure | How-to, workflows |
person | People information |
project | General project context |
temporary | Short-lived, pair with TTL |
bug | Known issues, workarounds |
learned | Lessons, insights |
config | Configuration, settings |
api | API details, endpoints |
What NOT to store
- Conversation transcripts (store conclusions, not chats)
- Trivial changes (typo fixes, single-line edits)
- Temporary debugging output
- Information already in CLAUDE.md or project docs
Anti-patterns
- Dumping everything into
global
- Storing without tags
- Recalling all search results
- Searching without a specific information need
- Writing narrative instead of distilled facts
