Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Python agent-contextagent-memoryagent-pluginsagentic-ragcontext-databasedsh-pluginknowledge-basememorymemory-managementself-evolvingvector-database
fix(docs): fix relative paths in README files to match actual docs structure (#122)
evpeoplec3325a097753
diff --git a/README.md b/README.mdindex e51a38fd0..65936b2f4 100644--- a/README.md+++ b/README.md@@ -19,7 +19,7 @@ English / [中文](README_CN.md)👋 Join our Community-📱 <a href="./docs/en/about/about-us.md#lark-group">Lark Group</a> · <a href="./docs/en/about/about-us.md#wechat-group">WeChat</a> · <a href="https://discord.com/invite/eHvx8E9XF3">Discord</a> · <a href="https://x.com/openvikingai">X</a>+📱 <a href="./docs/en/about/01-about-us.md#lark-group">Lark Group</a> · <a href="./docs/en/about/01-about-us.md#wechat-group">WeChat</a> · <a href="https://discord.com/invite/eHvx8E9XF3">Discord</a> · <a href="https://x.com/openvikingai">X</a></div>@@ -77,7 +77,7 @@ OpenViking requires the following model capabilities:OpenViking supports various model services:- **OpenAI Models**: Supports GPT-4V and other VLM models, and OpenAI Embedding models.-- **Volcengine (Doubao Models)**: Recommended for low cost and high performance, with free quotas for new users. For purchase and activation, please refer to: [Volcengine Purchase Guide](./docs/en/guides/volcengine-purchase-guide.md).+- **Volcengine (Doubao Models)**: Recommended for low cost and high performance, with free quotas for new users. For purchase and activation, please refer to: [Volcengine Purchase Guide](./docs/en/guides/02-volcengine-purchase-guide.md).- **Other Custom Model Services**: Supports model services compatible with the OpenAI API format.### 3. Environment Configuration@@ -280,7 +280,7 @@ After running the first example, let's dive into the design philosophy of OpenViWe no longer view context as flat text slices but unify them into an abstract virtual filesystem. Whether it's memories, resources, or capabilities, they are mapped to virtual directories under the `viking://` protocol, each with a unique URI.-This paradigm gives Agents unprecedented context manipulation capabilities, enabling them to locate, browse, and manipulate information precisely and deterministically through standard commands like `ls` and `find`, just like a developer. This transforms context management from vague semantic matching into intuitive, traceable "file operations". Learn more: [Viking URI](./docs/en/concepts/viking-uri.md) | [Context Types](./docs/en/concepts/context-types.md)+This paradigm gives Agents unprecedented context manipulation capabilities, enabling them to locate, browse, and manipulate information precisely and deterministically through standard commands like `ls` and `find`, just like a developer. This transforms context management from vague semantic matching into intuitive, traceable "file operations". Learn more: [Viking URI](./docs/en/concepts/04-viking-uri.md) | [Context Types](./docs/en/concepts/02-context-types.md)```viking://@@ -313,7 +313,7 @@ Stuffing massive amounts of context into a prompt all at once is not only expens- **L1 (Overview)**: Contains core information and usage scenarios for Agent decision-making during the planning phase.- **L2 (Details)**: The full original data, for deep reading by the Agent when absolutely necessary.-Learn more: [Context Layers](./docs/en/concepts/context-layers.md)+Learn more: [Context Layers](./docs/en/concepts/03-context-layers.md)```viking://resources/my_project/@@ -342,13 +342,13 @@ Single vector retrieval struggles with complex query intents. OpenViking has des4. **Recursive Drill-down**: If subdirectories exist, recursively repeat the secondary retrieval steps layer by layer.5. **Result Aggregation**: Finally, obtain the most relevant context to return.-This "lock high-score directory first, then refine content exploration" strategy not only finds the semantically best-matching fragments but also understands the full context where the information resides, thereby improving the globality and accuracy of retrieval. Learn more: [Retrieval Mechanism](./docs/en/concepts/retrieval.md)+This "lock high-score directory first, then refine content exploration" strategy not only finds the semantically best-matching fragments but also understands the full context where the information resides, thereby improving the globality and accuracy of retrieval. Learn more: [Retrieval Mechanism](./docs/en/concepts/07-retrieval.md)### 4. Visualized Retrieval Trajectory → Observable ContextOpenViking's organization uses a hierarchical virtual filesystem structure. All context is integrated in a unified format, and each entry corresponds to a unique URI (like a `viking://` path), breaking the traditional flat black-box management mode with a clear hierarchy that is easy to understand.-The retrieval process adopts a directory recursive strategy. The trajectory of directory browsing and file positioning for each retrieval is fully preserved, allowing users to clearly observe the root cause of problems and guide the optimization of retrieval logic. Learn more: [Retrieval Mechanism](./docs/en/concepts/retrieval.md)+The retrieval process adopts a directory recursive strategy. The trajectory of directory browsing and file positioning for each retrieval is fully preserved, allowing users to clearly observe the root cause of problems and guide the optimization of retrieval logic. Learn more: [Retrieval Mechanism](./docs/en/concepts/07-retrieval.md)### 5. Automatic Session Management → Context Self-Iteration@@ -357,7 +357,7 @@ OpenViking has a built-in memory self-iteration loop. At the end of each session- **User Memory Update**: Update memories related to user preferences, making Agent responses better fit user needs.- **Agent Experience Accumulation**: Extract core content such as operational tips and tool usage experience from task execution experience, aiding efficient decision-making in subsequent tasks.-This allows the Agent to get "smarter with use" through interactions with the world, achieving self-evolution. Learn more: [Session Management](./docs/en/concepts/session.md)+This allows the Agent to get "smarter with use" through interactions with the world, achieving self-evolution. Learn more: [Session Management](./docs/en/concepts/08-session.md)---@@ -426,7 +426,7 @@ The Viking team focuses on unstructured information processing and intelligent r- **Oct 2025**: Open-sourced [MineContext](https://github.com/volcengine/MineContext), exploring proactive AI applications.- **Jan 2026**: Open-sourced OpenViking, providing underlying context database support for AI Agents.-For more details, please see: **[About Us](./docs/en/about/about-us.md)**+For more details, please see: **[About Us](./docs/en/about/01-about-us.md)**---@@ -437,8 +437,8 @@ OpenViking is still in its early stages, and there are many areas for improvemen- Light up a precious **Star** for us to give us the motivation to move forward.- Visit our [**Website**](https://www.openviking.ai) to understand the philosophy we convey, and use it in your projects via the [**Documentation**](https://www.openviking.ai/docs). Feel the change it brings and give us feedback on your truest experience.- Join our community to share your insights, help answer others' questions, and jointly create an open and mutually helpful technical atmosphere:- - 📱 **Lark Group**: Scan the QR code to join → [View QR Code](./docs/en/about/about-us.md#lark-group)- - 💬 **WeChat Group**: Scan the QR code to add assistant → [View QR Code](./docs/en/about/about-us.md#wechat-group)+ - 📱 **Lark Group**: Scan the QR code to join → [View QR Code](./docs/en/about/01-about-us.md#lark-group)+ - 💬 **WeChat Group**: Scan the QR code to add assistant → [View QR Code](./docs/en/about/01-about-us.md#wechat-group)- 🎮 **Discord**: [Join Discord Server](https://discord.com/invite/eHvx8E9XF3)- 🐦 **X (Twitter)**:[Follow us](https://x.com/openvikingai)- Become a **Contributor**, whether submitting a bug fix or contributing a new feature, every line of your code will be an important cornerstone of OpenViking's growth.diff --git a/README_CN.md b/README_CN.mdindex fd1ec47e5..b4c45c863 100644--- a/README_CN.md+++ b/README_CN.md@@ -19,7 +19,7 @@👋 加入我们的社区讨论-📱 <a href="./docs/zh/about/about-us.md#飞书群">飞书群</a> · <a href="./docs/zh/about/about-us.md#微信群">微信群</a> · <a href="https://discord.com/invite/eHvx8E9XF3">Discord</a> · <a href="https://x.com/openvikingai">X</a>+📱 <a href="./docs/zh/about/01-about-us.md#飞书群">飞书群</a> · <a href="./docs/zh/about/01-about-us.md#微信群">微信群</a> · <a href="https://discord.com/invite/eHvx8E9XF3">Discord</a> · <a href="https://x.com/openvikingai">X</a></div>@@ -76,7 +76,7 @@ OpenViking 需要以下模型能力:OpenViking 支持多种模型服务:- **OpenAI 模型**:支持 GPT-4V 等 VLM 模型和 OpenAI Embedding 模型-- **火山引擎(豆包模型)**:推荐使用,成本低、性能好,新用户有免费额度。如需购买和开通,请参考:[火山引擎购买指南](./docs/zh/guides/volcengine-purchase-guide.md)+- **火山引擎(豆包模型)**:推荐使用,成本低、性能好,新用户有免费额度。如需购买和开通,请参考:[火山引擎购买指南](./docs/zh/guides/02-volcengine-purchase-guide.md)- **其他自定义模型服务**:支持兼容 OpenAI API 格式的模型服务### 3. 配置环境@@ -279,7 +279,7 @@ Search results:我们不再将上下文视为扁平的文本切片,而是将其统一抽象并组织于一个虚拟文件系统中。无论是记忆、资源还是能力,都会被映射到 `viking://` 协议下的虚拟目录,拥有唯一的 URI。-这种范式赋予了 Agent 前所未有的上下文操控能力,使其能像开发者一样,通过 `ls`、`find` 等标准指令来精确、确定性地定位、浏览和操作信息,让上下文的管理从模糊的语义匹配演变为直观、可追溯的"文件操作"。了解更多:[Viking URI](./docs/zh/concepts/viking-uri.md) | [上下文类型](./docs/zh/concepts/context-types.md)+这种范式赋予了 Agent 前所未有的上下文操控能力,使其能像开发者一样,通过 `ls`、`find` 等标准指令来精确、确定性地定位、浏览和操作信息,让上下文的管理从模糊的语义匹配演变为直观、可追溯的"文件操作"。了解更多:[Viking URI](./docs/zh/concepts/04-viking-uri.md) | [上下文类型](./docs/zh/concepts/02-context-types.md)```viking://@@ -312,7 +312,7 @@ viking://- **L1 (概述)**:包含核心信息和使用场景,供 Agent 在规划阶段进行决策- **L2 (详情)**:完整的原始数据,供 Agent 在确有必要时深入读取-了解更多:[上下文分层](./docs/zh/concepts/context-layers.md)+了解更多:[上下文分层](./docs/zh/concepts/03-context-layers.md)```viking://resources/my_project/@@ -341,13 +341,13 @@ viking://resources/my_project/4. **递归下探**:若目录下仍存在子目录,则逐层递归重复上述二次检索步骤5. **结果汇总**:最终拿到最相关上下文返回-这种"先锁定高分目录、再精细探索内容"的策略,不仅能找到语义最匹配的片段,更能理解信息所在的完整语境,从而提升检索的全局性与准确性。了解更多:[检索机制](./docs/zh/concepts/retrieval.md)+这种"先锁定高分目录、再精细探索内容"的策略,不仅能找到语义最匹配的片段,更能理解信息所在的完整语境,从而提升检索的全局性与准确性。了解更多:[检索机制](./docs/zh/concepts/07-retrieval.md)### 4. 可视化检索轨迹 → 上下文可观测OpenViking 的组织方式采用层次化虚拟文件系统结构,所有上下文均以统一格式整合且每个条目对应唯一 URI(如 `viking://` 路径),打破传统扁平黑箱式管理模式,层次分明易于理解。-检索过程采用目录递归策略,每次检索的目录浏览、文件定位轨迹均被完整留存,能够清晰观测问题根源并指导检索逻辑优化。了解更多:[检索机制](./docs/zh/concepts/retrieval.md)+检索过程采用目录递归策略,每次检索的目录浏览、文件定位轨迹均被完整留存,能够清晰观测问题根源并指导检索逻辑优化。了解更多:[检索机制](./docs/zh/concepts/07-retrieval.md)### 5. 会话自动管理 → 上下文自迭代@@ -356,7 +356,7 @@ OpenViking 内置了记忆自迭代闭环。在每次会话结束时,开发者- **用户记忆更新**:更新用户偏好相关记忆,使 Agent 回应更贴合用户需求- **Agent 经验积累**:从任务执行经验中提取操作技巧、工具使用经验等核心内容,助力后续任务高效决策-让 Agent 在与世界的交互中"越用越聪明",实现自我进化。了解更多:[会话管理](./docs/zh/concepts/session.md)+让 Agent 在与世界的交互中"越用越聪明",实现自我进化。了解更多:[会话管理](./docs/zh/concepts/08-session.md)---@@ -425,7 +425,7 @@ Viking 团队专注于非结构化信息处理和智能检索领域,在上下- **2025 年 10 月**:开源 [MineContext](https://github.com/volcengine/MineContext),主动式 AI 应用探索- **2026 年 1 月**:开源 OpenViking,为 AI Agent 提供底层上下文数据库支撑-更多详细信息请查看:**[关于我们](./docs/zh/about/about-us.md)**+更多详细信息请查看:**[关于我们](./docs/zh/about/01-about-us.md)**---@@ -436,8 +436,8 @@ OpenViking 目前还处于早期阶段,有许多需要完善和探索的地方- 为我们点亮一颗宝贵的 **Star**,给予我们前行的动力- 访问我们的 [**网站**](https://www.openviking.ai),了解我们传递的理念,并通过[**文档**](https://www.openviking.ai/docs)使用它,在您的项目中感受它带来的改变,并向我们反馈最真实的体验- 加入我们的社区,分享您的洞见,帮助解答他人的疑问,共同营造一个开放、互助的技术氛围:- - 📱 **飞书群**:扫描二维码加入 → [查看二维码](./docs/zh/about/about-us.md#飞书群)- - 💬 **微信群**:添加小助手微信,备注「OpenViking」→ [查看二维码](./docs/zh/about/about-us.md#微信群)+ - 📱 **飞书群**:扫描二维码加入 → [查看二维码](./docs/zh/about/01-about-us.md#飞书群)+ - 💬 **微信群**:添加小助手微信,备注「OpenViking」→ [查看二维码](./docs/zh/about/01-about-us.md#微信群)- 🎮 **Discord**:[加入 Discord 服务器](https://discord.com/invite/eHvx8E9XF3)- 🐦 **X (Twitter)**:[关注我们的动态](https://x.com/openvikingai)- 成为我们的**贡献者**,无论是提交一个 Bug 修复,还是贡献一个新功能,您的每一行代码都将是 OpenViking 成长的重要基石