| name | serena-memory |
| description | This skill should be used when the user asks to "save project context",
"load memories", "persist knowledge", "remember this for next session",
"update architecture notes", or mentions Serena's write_memory, read_memory,
list_memories, edit_memory tools.
|
Serena Memory Management
Memory Operations
| Operation | Tool |
|---|
| Save knowledge | write_memory(key, content) |
| Update existing | edit_memory(key, content) |
| Load knowledge | read_memory(key) |
| List all | list_memories() |
| Remove | delete_memory(key) |
Recommended Memory Keys
| Key | Purpose |
|---|
architecture_overview | System architecture |
code_conventions | Coding standards |
recent_changes | Latest commits |
known_issues | Bugs and workarounds |
test_patterns | Testing conventions |
session_context | Current task (preserved during compaction) |
When to Update Memories
- After exploration: Save architectural insights
- After debugging: Document root causes and fixes
- After refactoring: Record successful patterns
- Before compaction: Preserve current task context
- After commits: Summarize significant changes
Example: Architecture Memory
write_memory(
key="architecture_overview",
content="""
# Project Architecture
## Layers
- API: FastAPI routes in src/api/
- Services: Business logic in src/services/
- Models: SQLAlchemy models in src/models/
## Key Patterns
- Dependency injection via FastAPI Depends
- Repository pattern for data access
## Entry Points
- Main app: src/main.py
- CLI: src/cli.py
"""
)
Example: Code Conventions Memory
write_memory(
key="code_conventions",
content="""
# Code Conventions
- snake_case for functions/variables
- PascalCase for classes
- Type hints required for public functions
- Docstrings in Google style
- Tests in tests/ mirror src/ structure
"""
)
