Knowledge Graph & Institutional Intelligence
Connect people, sessions, messages, tools, commits and artifacts into a queryable history of work.
What this replaces
Similarity search can find related text but cannot reliably explain provenance, dependencies or how decisions and artifacts connect.
What your team gains
A graph representation of project activity that agents can query to answer who/what/when/how questions and generate narratives.
What is inside the blueprint
How it fits the platform
Sessions/events/artifacts -> graph ingest -> graph database -> graph queries/MCP + timeline-context API -> agents and timeline experiences.
Graph database, graph-mcp-server, timeline-context-api, journey-tracker
- AICORTEX Core PlatformThe graph database and its MCP/API services are deployed and routed by Core.
From prerequisites to operation
- Graph ontology/node/relationship model
- Event and artifact feeds
- Retention strategy
- Create graph schema/indexes
- Ingest sessions/messages/tool calls/commits/artifacts
- Expose MCP server
- Connect timeline/context API
- Build starter queries
- Node labels
- Relationship types
- Index strategy
- Vector dimensions where used
- Access policy
- Retention
- Graph growth
- Query performance
- Schema evolution
- Index maintenance
- Backups
What this unlocks with other layers
Institutional Memory
The AI can retrieve documents, recall prior work and trace relationships and provenance.
Research-to-Knowledge
Discovery becomes a retained, structured research corpus instead of disappearing after one chat.
AI SRE Foundation
Agents can reason over the same telemetry and history humans use for diagnosis.