OpenViking Context Database Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. OpenViking is an open source context database for AI Agents that replaces fragmented vector stores with a unified filesystem paradigm . It manages agent memory, resources, and skills in a tiered L0/L1/L2 structure, enabling hierarchical context delivery, observable retrieval trajectories, and self evolving session memory. Installation Python Package Optional Rust CLI Prerequisites Python 3.10+ Go 1.22+ (for AGFS components) GCC 9+ or Clang 11+ (for core extensions) Configuration Create ~/.openviking/ov.conf : Note: OpenViking reads api key values as strings; use environment variable injection at startup rather than literal secrets. Provider Options Role Provider Value Example Model VLM openai gpt 4o VLM volcengine doubao seed 2 0 pro 260215 VLM litellm claude 3 5 sonnet 20240620 , ollama/llama3.1 Embedding openai text embedding 3 large Embedding volcengine doubao embedding vision 250615 Embedding jina jina embeddings v3 LiteLLM VLM Examples Core Concepts Filesystem Paradigm OpenViking organizes agent context like a filesystem: Tiered Context Loading (L0/L1/L2) L0 : Always loaded — core identity, persistent preferences L1 : Loaded on demand — relevant resources fetched per task L2 : Semantically retrieved — skills pulled by similarity search This tiered approach minimizes token consumption while maximizing context relevance. Python API Usage Basic Setup Managing a Context Namespace (Agent Brain) Querying Context Session Memory & Auto Compression Retrieval Trajectory (Observable RAG) Common Patterns Pattern 1: Agent with Persistent Memory Pattern 2: Hierarchical Skill Loading Pattern 3: RAG over Codebase Pattern 4: Multi Agent Shared Context CLI Commands (ov cli) Troubleshooting Config Not Found Embedding Dimension Mismatch If you switch embedding models, the stored vector dimensions will conflict: Workspace Permission Errors LiteLLM Provider Not Detected High Token Usage Enable tiered loading to reduce L1/L2 fetches: Slow Indexing on Large Codebases Environment Variables Reference Variable Purpose OV CONFIG Path to ov.conf override OPENAI API KEY OpenAI API key for VLM/embedding ANTHROPIC API KEY Anthropic Claude via LiteLLM DEEPSEEK API KEY DeepSeek via LiteLLM GEMINI API KEY Google Gemini via LiteLLM OV LOG LEVEL Override log level ( DEBUG , INFO , WARN ) OV WORKSPACE Override workspace path Resources Website : https://openviking.ai Docs : https://www.openviking.ai/docs GitHub : https://github.com/volcengine/OpenViking Issues : https://github.com/volcengine/OpenViking/issues Discord : https://discord.com/invite/eHvx8E9XF3 LiteLLM Providers : https://docs.litellm.ai/docs/providers

openviking-context-database