OpenViking

项目详情摘要

OpenViking: The Context Database for AI Agents English / 中文 / 日本語 Website · Live Demo · GitHub · Issues · Docs 👋 Join our Community 📱 Lark Group · WeChat · Discord · X What is OpenViking OpenViking is an open-source context database for AI agents. It gives agents a place to store knowledge, remember users, and reuse experience across sessions. OpenViking organizes context as a virtual filesystem under `viking://`. Agents can operate on it like files: use `ls`, `tree`, `read`, and `write` to browse directories, read, create, and edit content, or search within a directory. Directory summaries support on-demand loading. Try OpenViking Studio in your browser, no installation required. Self-host Web Studio. Why OpenViking **One filesystem for all context.** Resources hold documents and code; memories retain user preferences and experience; skills define how to perform tasks. Each has a `viking://` URI for browsing and retrieval. → Viking URI · Context types **Load only the context you need.** Directory abstracts (L0) and overviews (L1) help agents decide when to read full content (L2). → Context layers **Search within the directory structure.** Vector search finds candidate directories, then explores their contents. `find` runs a query directly; `search` can use session context to plan retrieval. → Retrieval **Turn sessions into memory.** Committing a session archives the conversation and starts background extraction. Memory policies control what is retained; candidates are compared with existing memories for creation, merging, or skipping. With VikingBot enabled, `ov compile` uses a skill to organize source material into a wiki, knowledge graph, or report. → Sessions · Context compilation Architecture · Design rationale The three loading tiers: **L0 (Abstract)**: a one-sent