{"name":"OpenViking: A Self-Evolving Context Database for AI Agents","description":"OpenViking is an open-source context database designed for AI agents, unifying agent memory, knowledge RAG, and skills into a virtual filesystem. It allows agents to browse their context deterministically using familiar commands like `ls` and `tree`. This innovative approach aims to enhance agent performance and reduce token spend by loading content in tiered layers.","github":"https://github.com/volcengine/OpenViking","url":"https://osrepos.com/repo/volcengine-openviking","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/volcengine-openviking","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/volcengine-openviking.md","json":"https://osrepos.com/repo/volcengine-openviking.json","topics":["AI Agents","Context Database","Agent Memory","RAG","Python","Self-Evolving AI","Agent Plugins","LLM Applications"],"keywords":["AI Agents","Context Database","Agent Memory","RAG","Python","Self-Evolving AI","Agent Plugins","LLM Applications"],"stars":null,"summary":"OpenViking is an open-source context database designed for AI agents, unifying agent memory, knowledge RAG, and skills into a virtual filesystem. It allows agents to browse their context deterministically using familiar commands like `ls` and `tree`. This innovative approach aims to enhance agent performance and reduce token spend by loading content in tiered layers.","content":"## Introdução\n\nOpenViking is an open-source context database specifically designed for AI agents. It unifies agent memory, knowledge RAG, and skills into a single virtual filesystem, accessible via the `viking://` protocol. This innovative approach allows AI agents to browse and manage their context deterministically, using familiar commands like `ls`, `tree`, and `find`, rather than querying a black-box vector store. Content is processed into three tiers, L0 abstract, L1 overview, and L2 details, and loaded on demand, significantly reducing token spend and improving efficiency. Every retrieval leaves a trajectory, making debugging and observation straightforward.\n\n## Porquê usar OpenViking\n\nOpenViking offers several compelling advantages for developing and deploying AI agents:\n\n*   **One filesystem for all context:** Memories, resources, and skills are organized under `viking://` URIs, enabling agents to locate and manipulate context deterministically, similar to a developer working with files. This provides a structured and predictable environment for agent operations.\n*   **Tiered loading cuts token spend:** Each entry is processed into L0 (abstract), L1 (overview), and L2 (details) layers upon writing. Content is then loaded only as deep as the current task requires, optimizing token usage and reducing operational costs.\n*   **Directory recursive retrieval:** Vector search first identifies the highest-scoring directory, then drills down layer by layer. This ensures that retrieval results arrive with their surrounding context intact, providing richer and more relevant information to the agent.\n*   **Observable retrieval:** Every query preserves its directory-browsing trajectory. If a result seems incorrect, developers can trace the exact path that produced it, greatly aiding debugging and understanding of agent behavior.\n*   **Sessions become memory:** After a session commits, OpenViking asynchronously extracts user preferences and agent experience, integrating them into long-term memory. This allows agents to learn and evolve over time, improving their performance and personalization.\n\nOpenViking has demonstrated significant improvements in user memory accuracy and agent task success, as detailed in its benchmark reports.\n\n## Instalação\n\nTo get started with OpenViking, ensure you have Python 3.10 or higher installed. For a quick hands-on experience without installation, you can try the [OpenViking Studio](https://openviking.ai/studio \"OpenViking Studio Live Demo\" target=\"_blank\") live demo.\n\nFor local installation:\n\nbash\npip install openviking --upgrade\nopenviking-server init      # interactive wizard: providers, models, ov.conf\nopenviking-server doctor    # validate setup\nopenviking-server           # start (background: nohup openviking-server > openviking.log 2>&1 &)\n\n\nThe `init` command guides you through provider setup, supporting Volcengine, OpenAI, Codex OAuth, Kimi, GLM, and local Ollama. The `doctor` command verifies your configuration, Python version, provider connectivity, and disk space.\n\n## Exemplos de Uso\n\nOnce the OpenViking server is running, you can interact with it using the `ov` client CLI:\n\nbash\nov status\nov add-resource https://github.com/volcengine/OpenViking # --wait\nov ls viking://resources/\nov tree viking://resources/volcengine -L 2\n# wait some time for semantic processing if not --wait\nov find \"what is openviking\"\nov grep \"openviking\" --uri viking://resources/volcengine/OpenViking/docs/en\n\n\nOpenViking also offers integrations with various AI agents, including Claude Code, Codex, OpenClaw, Hermes, LangChain, and more, allowing you to inject OpenViking recall into your agent's context and auto-commit session memory.\n\n## Links Úteis\n\nExplore OpenViking further through these official resources:\n\n*   **Website:** [https://openviking.ai/](https://openviking.ai/ \"OpenViking Website\" target=\"_blank\")\n*   **Live Demo (OpenViking Studio):** [https://openviking.ai/studio](https://openviking.ai/studio \"OpenViking Studio Live Demo\" target=\"_blank\")\n*   **GitHub Repository:** [https://github.com/volcengine/OpenViking](https://github.com/volcengine/OpenViking \"OpenViking GitHub Repository\" target=\"_blank\")\n*   **Documentation:** [https://docs.openviking.ai/](https://docs.openviking.ai/ \"OpenViking Documentation\" target=\"_blank\")\n*   **Blog:** [https://blog.openviking.ai/](https://blog.openviking.ai/ \"OpenViking Blog\" target=\"_blank\")\n*   **Discord Community:** [https://discord.com/invite/eHvx8E9XF3](https://discord.com/invite/eHvx8E9XF3 \"OpenViking Discord\" target=\"_blank\")\n*   **X (Twitter):** [https://x.com/openvikingai](https://x.com/openvikingai \"OpenViking on X\" target=\"_blank\")","metrics":{"detailViews":3,"githubClicks":1},"dates":{"published":null,"modified":"2026-08-29T12:23:03.000Z"}}