agent memory plugin based on CLP

Key features

• Structured memoryEvery item has a scope, kind (fact, constraint, procedure, skill…), tags, and source
• Evolving memory for agents — recall before the model thinks, reflect after it answers.
• RecallBefore each prompt, assemble relevant memories into the agent's context
• First-class skillsProcedural SOPs separate from declarative memories, with lessons learned tracking and a dedicated Skills tab in the Memory panel
• Batch distillationTurns are collected and distilled in batches for better memory quality