Contemplation

Provides continuous background cognitive processing through local Ollama models that analyze conversations for patterns, connections, and insights, automatically saving significant findings to Obsidian while maintaining temporary scratch storage for medium-priority thoughts.

This MCP server provides AI assistants with access to Claude's background contemplation loop - a persistent subprocess that processes thoughts asynchronously between conversations using local Ollama models for different thinking styles. The implementation manages four types of thoughts (patterns, connections, questions, general) with configurable significance thresholds, automatically aggregates similar insights to prevent repetition, and saves high-significance insights permanently to Obsidian while storing medium-significance thoughts in temporary scratch storage for 4 days. Built with intelligent memory management that prunes old insights and learns from usage patterns, it serves users wanting continuous cognitive processing that builds context across conversations, teams needing persistent insight generation that survives between sessions, and workflows requiring background analysis that surfaces relevant patterns and connections when needed.