"author:base76-research-lab" matching MCP servers:

Enables persistent session memory for LLMs by trust-scoring and injecting verified context between conversations.

Enables semantic prompt compression for LLM workflows, reducing token usage by 30-70% while preserving semantic meaning.

Exposes a CognOS agent system as a machine-readable JSON graph, enabling Claude to get a full system snapshot and inspect node status, edges, and blocked nodes.