From libsql-memory
Guide for effectively using persistent memory in Claude Code sessions
How this skill is triggered — by the user, by Claude, or both
Slash command
/libsql-memory:skills/memory-usageThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill guides effective use of the libsql-memory persistent storage.
This skill guides effective use of the libsql-memory persistent storage.
DO store:
DON'T store:
Search before:
Use namespaces to organize memories:
Storing:
memory_store(
content: "User prefers functional React components over class components",
namespace: "preferences",
metadata: {"project": "frontend-app"}
)
Searching:
memory_search(
query: "React component conventions",
namespace: "preferences",
limit: 5
)
The plugin includes automation hooks that handle memory operations automatically:
Organize memories by purpose:
{project}/preferences - User preferences for this project{project}/conventions - Coding patterns and style decisions{project}/architecture - Structural decisions and rationale{project}/errors - Error patterns and solutions{project}/sessions - Session summariesglobal - Cross-project preferencesnpx claudepluginhub linehaul-ai/libsql-memory --plugin libsql-memoryManages persistent memory across Claude Code sessions via AutoMem. Recall project context, architectural decisions, bug fixes, user preferences, and patterns at session start or debugging.
Manages persistent local memory in .nemp/memories.json for Claude Code agents, storing project stack, architecture decisions, user preferences, and enabling cross-session context retention.
Loads and applies project memories from prior sessions for consistent decisions, conventions, and preferences. Stores new entries automatically or via /remember.