Knowledge Architecture

Three Knowledge Layers:

+------------------------------------------------------------------+
|                     LETTA SERVER (v0.16.6)                        |
|                                                                   |
|  LAYER 3: Agent Memory           LAYER 1: Letta Archives         |
|  (per-agent, in-context)         (shared, searchable)             |
|                                                                   |
|  +------------------+            +---------------------------+    |
|  | persona          |            | fxyz-network              |    |
|  | human            |            |   brand, tokenomics, arch |    |
|  | context          |            | fxyz-compliance           |    |
|  | preferences      |            |   MiCA, VASP, regs        |    |
|  +------------------+            | fxyz-market               |    |
|                                  |   FX theory, math models  |    |
|  LAYER 2: Graphiti (MCP)         | fxyz-graph                |    |
|  (temporal, conversational)      |   Cypher, schema, ontology|    |
|                                  +---------------------------+    |
|  +---------------------------+                                    |
|  | search_facts              |                                    |
|  | search_nodes              |                                    |
|  | add_episode               |                                    |
|  | get_episodes              |                                    |
|  +------------+--------------+                                    |
+---------------|---------------------------------------------------+
                | streamable_http (MCP)
                v
+------------------------------------------------------------------+
|              GRAPHITI SERVICE (zepai/knowledge-graph-mcp)         |
|                                                                   |
|  graphiti-core: entity extraction, temporal edges, deduplication  |
|  group_id isolation: shared:network | member:{id} | circle:{id}  |
|                                                                   |
|  Connects to: FalkorDB (internal graph store, NOT fxyz Neo4j)     |
|  LLM:         Claude Haiku (entity extraction)                   |
|  Embeddings:  openai/text-embedding-3-small (1536 dim)           |
+------------------------------------------------------------------+
                |
                v
+------------------------------------------------------------------+
|                     FALKORDB (Graphiti-internal)                   |
|                                                                   |
|  Graphiti nodes: :Entity, :EpisodicNode, :CommunityNode          |
|  Isolation: group_id property on all Graphiti nodes               |
|  NOTE: This is Graphiti's own graph DB, separate from fxyz Neo4j  |
+------------------------------------------------------------------+

# docker-compose.graphiti.yaml
services:
  graphiti:
    image: zepai/knowledge-graph-mcp:latest
    container_name: graphiti-mcp
    hostname: graphiti-server
    environment:
      MODEL_NAME: claude-haiku-4-5     # entity extraction (cheap, fast)
      EMBEDDING_MODEL: openai/text-embedding-3-small
      EMBEDDING_DIM: "1536"
      OPENAI_API_KEY: ${OPENAI_API_KEY}
    ports:
      - "8199:8199"
    # Graphiti uses FalkorDB internally (bundled or sidecar),
    # NOT the fxyz Neo4j instance

1. Documentation (markdown, MDX, research docs)
   |
   v  [POST /api/fixie/archives/ingest]
2. Letta Archives (chunked passages, searchable)
   |
   v  [archival_memory_search]
3. Agent Conversations (agent reads archives, answers member questions)
   |
   v  [add_episode]
4. Graphiti (entity extraction, temporal edges, deduplication)
   |
   v  [search_facts, search_nodes]
5. Future Conversations (agent recalls learned facts, refines answers)