Volcano Engine's OpenViking pitches a filesystem for agent memory
Volcano Engine has open-sourced OpenViking, a context database for AI agents that organizes knowledge, memories and skills into one virtual filesystem under the viking:// scheme, navigable with file-like operations such as ls, tree, read, write and grep. Each directory carries generated summaries in three tiers — an L0 one-sentence abstract, an L1 overview and L2 full content — so agents can judge relevance before loading details, and committing a session archives the conversation and extracts memories as editable Markdown. The project says version 0.3.22 was evaluated on LoCoMo long-conversation user memory and tau2-bench multi-turn agent tasks, and it ships a no-install browser Studio plus memory plugin installers for Claude Code, Codex, Cursor, TRAE and OpenCode.
OpenViking argues most agent memory is an opaque black box and instead offers inspectable, directory-scoped retrieval over context.
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

The Context Database for AI Agents
#OpenViking#Volcano Engine#Claude Code#Codex#Cursor#TRAE#OpenCode#VikingRAG#Doubao 2.0 Pro