Plugin Claude Code
Persistent memory with outcome-based learning for AI coding agents. Stores knowledge from coding sessions, learns which memories actually help, and gets smarter over time.
Command Claude Code
Archive/delete a memory by ID.
Command Claude Code
List all stored memories.
Command Claude Code
Show active memories loaded for the current context.
Command Claude Code
Record feedback on whether a memory helped (worked/failed/partial).
Command Claude Code
Explicitly search memories (usually handled automatically by Agent Skills).
Command Claude Code
Store a memory with optional category for future retrieval.
Hook Claude Code
Runs when a session starts, running mem context --project "$PWD" --limit 10 --format brief. From runtimenoteslabs/memory-layer.
Hook Claude Code
Runs when a session ends, running an inline shell check. From runtimenoteslabs/memory-layer.
Hook Claude Code
Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From runtimenoteslabs/memory-layer.
Settings file Claude Code
Agent settings declaring 3 hook events (SessionStart, SessionEnd, PostToolUse).
Skill Claude CodeCodex
Surfaces relevant coding patterns and conventions when writing new code.
Skill Claude CodeCodex
Automatically retrieve relevant memories when user asks about past decisions, conventions, or patterns.
Skill Claude CodeCodex
Prompts for outcome feedback after solutions that used memory context.
MCP server Claude CodeCodexCursor +2
MCP server "memory-layer" as configured in runtimenoteslabs/memory-layer. Launched with mem serve --mcp. Needs 2 environment variables to run.