OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Star Growth
Overview
OpenViking is an open-source context database for AI agents that organizes knowledge, memory, and skills as a virtual filesystem under a `viking://` URI scheme. It provides a structured way for agents to store, retrieve, and navigate context using filesystem-like commands (ls, read, write, grep) with generated summaries for directories. The system includes features for session archiving, semantic search scoped to subtrees, and context compilation into wikis or reports.
Deep Analysis
Organizes agent context as an inspectable virtual filesystem with URI addresses instead of a black-box embedding store.
⚡ Capabilities
- • Virtual filesystem organization of agent context
- • Semantic search scoped to directories
- • Generated directory summaries (L0/L1 abstracts)
- • Session archiving and memory extraction
- • Context compilation into wikis/knowledge graphs
🔗 Integrations
✓ Best For
- ✓ Developers needing structured agent memory
- ✓ Projects requiring inspectable and editable agent knowledge
- ✓ Teams wanting a unified filesystem for agent context
✗ Not Ideal For
- ✗ End-users seeking generic AI chatbots
- ✗ Simple key-value storage needs
- ✗ Non-AI applications
⚠ Known Limitations
- ⚠ Requires understanding of filesystem-like context management
- ⚠ Primarily developer-focused with CLI/API access
Alternatives
Compare OpenViking
Maintain OpenViking?
Show your live rank in your README, or put OpenViking in front of every visitor to AgentoolRank.