Pinned Loading

1. Progressive-Discovery-Spine Progressive-Discovery-Spine Public

   The missing architectural layer above MCP. Production patterns for LLM agents wired to enterprise systems at scale — without context blowout, hallucinated tool selection, or audit gaps.

   2

2. Agent-Governance-Spine Agent-Governance-Spine Public

   Architectural pattern for deterministic policy enforcement + per-agent identity + tamper-evident audit at the protocol layer for AI agent systems. Fifth spec in the SaaSquach AI Labs catalog (PDS, …

3. External-Signal-Fabric External-Signal-Fabric Public

   Architectural pattern for the optional capability layer that gives AI agents access to external-world signals when they need them — markets, logistics, geopolitics, supplier health, weather. Peer t…

4. Adversarial-Coordination-Spine Adversarial-Coordination-Spine Public

   Architectural pattern for the multi-agent coordination layer above PDS and MCP. Adversarial verification, file-system state, negotiated contracts, Planner/Generator/Evaluator role decomposition. Co…

5. Durable-Context-Spine Durable-Context-Spine Public

   DCS — Durable Context Spine: the temporal-persistence layer of the Spine. AI agent state, memory, and knowledge that survive across sessions and the passage of time. Open spec — CC BY 4.0 + MIT.

6. memcask memcask Public

   memcask — durable, tamper-evident context for AI agents in one file (zero deps). The SQLite of agent memory. Reference implementation of the Durable Context Spine.

   Python