What problem does it solve? AI agents lose all knowledge of the user between conversations, forcing repetitive re-explanation and preventing personalized, continuous assistance. This Skill configures Honcho memory for Hermes so user preferences, facts, and session context persist across conversations and across multiple agent profiles. ## Core Features & Use Cases - Cross-Session User Modeling: Honcho builds a persistent representation of each user, injecting session summaries, user representations, and peer cards into the system prompt automatically. - Multi-Profile Peer Isolation: Each Hermes profile gets its own AI peer while sharing a unified view of the user, so specialized agents develop independent identities. - Tunable Dialectic Reasoning: Three orthogonal knobs (cadence, depth, level) control how often, how many rounds, and how intensely Honcho's reasoning engine synthesizes answers. - Five Memory Tools: honcho_profile, honcho_search, honcho_context, honcho_reasoning, and honcho_conclude give the agent bidirectional read/write access to user and AI peer memory. - Use Case: A developer runs separate "coder" and "writer" Hermes profiles; both remember the user's preferences, while each maintains its own self-knowledge and observation settings. ## Quick Start Set up Honcho memory for my Hermes agent by running the interactive setup wizard and verifying the connection with the status command.
