asimons81/hermes-dreaming

Self-improvement loop for Hermes Agent: reads its own trajectory, proposes and applies the smallest skill/memory edit (create/patch), journaled with rollback. /refine command, refine_run tool, on_session_end hook.

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

Nightly deterministic memory consolidation ("dreaming") skill for Hermes Agent

Self-improvement system for Hermes Agent. Monitors performance, finds weak skills, fixes them with self-evolution, reports results.

Self-memory and replacement models for Hermes agents. Remember your work. Train your replacement.

The agent that grows with you

A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.

Finch: self-improvement orchestrator — mines session history to detect corrections, breakthroughs, and behavioral patterns.

Memory that lasts and compounds. MentisDB gives agents durable memory so they do not just remember, they improve over time. It stores append-only thought chains plus a Git-like skills registry, letting skills evolve with experience through versioned, integrity-checked updates and fast retrieval.