session-wrap

Capture session learnings by scanning active conversation history to extract decisions, corrections, and patterns, then updating project memory files to prevent knowledge loss and ensure continuous AI improvement.

Memory drift detection works by identifying workflow pattern deviations in active conversation sessions and surfacing them, allowing you to correct system rules and maintain long-term project consistency across interactions.

Automatically update CLAUDE.md rules and MEMORY.md files by running a session wrap that suggests system maintenance updates based on extracted insights, decisions, and corrections discovered during the active conversation.

Yes, automated knowledge capture requires integration with local memory files and session indexing hooks to maintain a coherent knowledge base and successfully extract actionable insights from active conversation sessions.

Run a session wrap at the end of a complex work session, such as a GTM strategy meeting, to document new client preferences, successful prompting strategies, and key decisions for application in the next session.

Your AI assistant forgets corrections due to knowledge loss between sessions without systematic capture; running a session wrap extracts and stores actionable insights, decisions, and workflow patterns in project memory files for continuous improvement.