{"id":"08143065-a2bb-418b-bee7-a6c385d4c8e8","kind":"products","code":"UB-D6614","name":"OpenViking","nameBasis":"original-brand","summary":"OpenViking is an open source AI Agent context database initiated and maintained by the ByteDance Volcano Engine Viking team for agent developers and AI application teams. It manages knowledge, long-term memory, and skills in a unified way, helping to solve the problems of agents losing context across sessions, dispersion of data, and difficulty in reusing work experience. Users can import documents, web pages, or code repositories, and then plug OpenViking into an existing agent. The system organizes the content into browsable directories and generates summaries and overviews, allowing the agent to read the required information according to the task. It provides both retrieval capabilities and support for viewing and editing the content saved by the agent, facilitating the continuous maintenance of knowledge and memory. Unified context management of core functions: Put documents, code materials, user memories and skills into the same directory structure, support browsing, searching and reading, and facilitate the management of information available to the agent. Layered on-demand reading: Generate a summary, overview, and retain the original text for the content. The agent can judge the relevance first, and then read the details to reduce loading a large amount of data at once. Long-term memory across sessions: After the session is submitted, user preferences, events, and work experience are extracted based on the content of the conversation to update the existing memory and preserve a useful background for subsequent tasks. Existing agent access: support access to Claude Code, Codex, Cursor, etc.","description":"OpenViking is an open source AI Agent context database initiated and maintained by the ByteDance Volcano Engine Viking team for agent developers and AI application teams. It manages knowledge, long-term memory, and skills in a unified way, helping to solve the problems of agents losing context across sessions, dispersion of data, and difficulty in reusing work experience. Users can import documents, web pages, or code repositories, and then plug OpenViking into an existing agent. The system organizes the content into browsable directories and generates summaries and overviews, allowing the agent to read the required information according to the task. It provides both retrieval capabilities and support for viewing and editing the content saved by the agent, facilitating the continuous maintenance of knowledge and memory. Unified context management of core functions: Put documents, code materials, user memories and skills into the same directory structure, support browsing, searching and reading, and facilitate the management of information available to the agent. Layered on-demand reading: Generate a summary, overview, and retain the original text for the content. The agent can judge the relevance first, and then read the details to reduce loading a large amount of data at once. Long-term memory across sessions: After the session is submitted, user preferences, events, and work experience are extracted based on the content of the conversation to update the existing memory and preserve a useful background for subsequent tasks. Existing agent access: support access to Claude Code, Codex, Cursor, etc.","country":null,"category":"Productivity","originalName":"OpenViking","eventDate":null,"website":null,"sourceUpdatedAt":"2026-10-27T14:00:23.513Z","englishUpdatedAt":"2026-10-28T00:56:06.605Z","reviewedAt":"2026-10-28T00:56:06.605Z","snapshotAt":"2026-10-28T00:47:51.550Z","sourceHash":"315ff6e0ff408c25fc6708a4c38f5488cb09813211f3813c7af13b0ff84a5ef6","companyId":"1b02538b-c982-4930-bba6-3c748a081154","foundedYear":null,"logoUrl":null,"originalText":"OpenViking 是字节跳动火山引擎 Viking 团队发起并维护的开源 AI Agent 上下文数据库，主要面向智能体开发者和 AI 应用团队。它统一管理知识资料、长期记忆和技能，帮助解决智能体跨会话丢失背景、资料分散以及工作经验难以复用的问题。用户可以导入文档、网页或代码仓库，再将 OpenViking 接入现有智能体。系统把内容组织成可浏览的目录，并生成摘要和概览，让智能体根据任务读取所需信息。它既提供检索能力，也支持查看和编辑智能体保存的内容，便于持续维护知识与记忆。核心功能统一上下文管理：将文档、代码资料、用户记忆和技能放入同一套目录结构，支持浏览、搜索和读取，方便管理智能体可用的信息。分层按需读取：为内容生成摘要、概览并保留原文，智能体可以先判断相关性，再读取细节，减少一次性加载大量资料。跨会话长期记忆：提交会话后，根据对话内容提取用户偏好、事件和工作经验，更新已有记忆，为后续任务保留有用背景。现有智能体接入：支持接入 Claude Code、Codex、Cursor 等工具，也提供 MCP、SDK 和 HTTP API，便于为已有应用增加知识检索与记忆能力。","sources":[],"related":[{"id":"1b02538b-c982-4930-bba6-3c748a081154","kind":"companies","code":"UB-C12567","name":"OpenViking","nameBasis":"source-english","summary":"Context Database for AI Agents","description":"OpenViking is an open-source context database for AI agents. Organize memory, resources, and skills, retrieve context, and connect your agent harness.","country":null,"category":null,"originalName":"OpenViking","eventDate":null,"website":"https://openviking.ai/","sourceUpdatedAt":"2026-10-26T00:00:00.000Z","englishUpdatedAt":"2026-11-01T02:03:52.499Z","reviewedAt":"2026-11-01T02:03:52.499Z","snapshotAt":"2026-11-01T00:40:31.077Z","sourceHash":"846335f3897e8759fdbbb0b3c48062695bb336866a6e9bea72aa9b954d3fea72","companyId":null,"foundedYear":null,"logoUrl":null,"path":"/companies/openviking"}],"path":"/products/openviking","structured":{"city":null,"country":null,"location":null,"role":null,"category":"Productivity","company":{"name":"OpenViking","path":"/companies/openviking"}},"definition":"OpenViking is a product in the Productivity category from OpenViking.","summaryBasis":"translated","thin":false,"canonical":"https://uniquebase.ai/products/openviking"}