semantic-memory-mcp

What problem does it solve?

Agents often miss relevant past findings, decisions, and bug root-causes because semantic memory is unused or underutilized; this Skill ensures agents proactively search, recall, and store concise vectorized memories so future investigations and decisions are faster and more accurate.

Core Features & Use Cases

• Proactive Memory Use: Rules for when to run semantic_search and semantic_recall at task start and during unexpected errors to surface relevant context.
• Structured Memory Writing: Guidance for write-capable agents to store reusable insights with content_type, tags, and brief rationale so others can act on them.
• Fallback and Safety: File-based fallback when MCP services are unavailable and quality gates to avoid storing speculative or task-specific noise.
• Use Case: A debugger encountering an intermittent "attached to a different loop" error runs semantic_search to find prior fixes, retrieves a formatted memory via semantic_recall, and semantic_store saves the verified root cause for future agents.

Quick Start

Ask the agent to proactively search and recall related memories for your task and, if it discovers a verified reusable insight, store it with tags and a brief rationale.