Concepts and principles
Follow this reading path through OpenViking's context model, processing flow, architecture and governance. If you have not used OpenViking yet, import and retrieve your first document, then return here to understand how the result was produced.
Start with the context model
Read these three pages in order to understand what is stored, where it lives and how much to read:
- Context Types: the roles of resources, memories and skills.
- Viking URI: how to locate context and distinguish user, Peer and shared spaces.
- Context Layers (L0/L1/L2): the relationship between abstracts, overviews and source content, including the limits of layered reading.
Follow processing and memory
Trace the paths from source ingestion and recorded conversations:
- Context Extraction: how sources are parsed, organized and processed semantically.
- Retrieval Mechanism: how relevant context is found and how
finddiffers fromsearch. - Session Management: how messages, session commits and memory extraction connect.
When you are ready to build, choose an application workflow. Look up parameters and responses in the reference.
Explore architecture and governance by question
| Question | Reading path |
|---|---|
| How do modules work together, and where is data stored? | Architecture Overview → Storage Architecture |
| When is processing complete, and how does recovery work? | Queue State and Completion Semantics → Path Locks and Crash Recovery |
| How do primary and backup writes, reads and observation work? | Multi-Write Storage → Metrics |
| Who can see which content, and how are permissions inherited? | Multi-Tenant → Resource Access Control (ACL) |
| How are data encrypted and skill privacy handled? | Data Encryption → Privacy Configs and Skill Privacy Extraction/Restore |
Configuration and deployment steps live in Deploy & Operate. Concept pages explain behavior and constraints; task guides explain how to configure and verify them, with links between the two.
See an application example
VikingBot shows how an agent combines context with multiple conversation channels. To run it, continue to VikingBot Installation and Configuration. For other existing tools, choose an agent integration.