Marketplace / Blueprint 05
LIVEKnowledge / knowledge

Persistent AI Memory

Let agents recall relevant history across sessions instead of starting over.

Review my build

Interactive platform map

Architecture in context

The focused blueprint, its required foundation, and declared recommendations.

Core Selected Automatic Required path
Blueprint 05 / Knowledge

Persistent AI Memory

Let agents recall relevant history across sessions instead of starting over.

1 vCPU2 GB RAM4 services
01 / Problem

What this replaces

Even powerful agents lose continuity when a session ends, forcing people to repeat project history, decisions and context.

02 / Outcome

What your team gains

A semantic session-history layer that can be searched through MCP or HTTP and injected into active work.

03 / Capability

What is inside the blueprint

Session capture and chunking
Vectorized historical recall
Semantic similarity retrieval
Bearer-auth HTTP access
MCP access
Historian persona/workflows
Cross-session project continuity
Foundation for user/team long-term memory
04 / Architecture

How it fits the platform

Conversation/session history -> embeddings -> recall.chunks in pgvector -> session-recall-mcp -> AI clients/personas.

Included services

session-recall-mcp, PostgreSQL, pgvector, embedding endpoint

Platform requirements
05 / Delivery

From prerequisites to operation

Prerequisites
  1. Captured session history
  2. Embedding pipeline
  3. Memory access/privacy policy
Deployment
  1. Create recall schema/index
  2. Ingest historical sessions
  3. Deploy MCP/HTTP service
  4. Register with supported clients
  5. Create memory retrieval instructions
Configuration
  1. Chunking
  2. Namespaces/tenants
  3. Similarity threshold
  4. Maximum recall context
  5. Retention and deletion rules
  6. Authentication
Operations
  1. Index growth
  2. Privacy boundaries
  3. Duplicate/stale memories
  4. Embedding migrations
  5. Retention enforcement
06 / Combinations

What this unlocks with other layers

Knowledge Hub & RAG + Persistent AI Memory + Knowledge Graph & Institutional Intelligence

Institutional Memory

The AI can retrieve documents, recall prior work and trace relationships and provenance.

AI Operations Center + MCP Agent Hub + Persistent AI Memory + Knowledge Graph & Institutional Intelligence

AI SRE Foundation

Agents can reason over the same telemetry and history humans use for diagnosis.

07 / Technology

Technology behind this capability

PostgreSQLRUNNING - three separate DB instances in censuspgvectorRUNNING in enterprise DB imageEmbeddingGemma + llama.cppRUNNING - low-utilization local embedderModel Context Protocol (MCP)MULTIPLE RUNNING SERVERSsession-recall-mcpAICORTEX native