volcengine/OpenViking
A live context database unifying memory, RAG, and skills — a concrete agent-memory architecture to test against Semantica.
Activity
Pushed Sep 9; embedding cache, plugin filters, compile queue/security work today.
What to Study
Context-database lifecycle, recall/capture filters, embeddings, skills/URI namespaces, and plugin integration.
Why It Matters
A live context database that unifies memory, RAG, and skills gives a concrete agent-memory architecture to test.
Action
Run sandboxed; trace recall/capture; compare retrieval quality and cost with Semantica.
Notes
- Candidate for the Context Graph vs. Context Database benchmark
- Cross-referencing against Research Paper Radar's graph-memory findings
AutoNateAI Experiments Using This
ProposedProcedural Graph Runtime
Can a validation-gated, self-evolving execution graph improve long-horizon agent workflows without increasing unsafe tool use?
hub Inspectable Agent Systems
ProposedIndependent Test Agent
Does separating an independent Test agent from a Repair agent reduce false-confidence patches without hurting resolution rate?
hub Inspectable Agent Systems
ProposedRevocable Memory Graph
Can a graph-based retriever enforce memory revocation structurally while still preserving useful personalized context?
hub Inspectable Agent Systems
ProposedSafety Judge Stress Lab
Which content-invariant wrapper transformations produce the highest disagreement across automated safety judges, and can simple ensembles resist them?
hub Inspectable Agent Systems
ProposedContext Graph vs. Context Database
Does explicit graph structure improve retrieval traceability and multi-hop reasoning over a context-database approach, at the same token cost?
hub Inspectable Agent Systems