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
docs: add DeerFlow agent access guide (#3960)
ManAsWindb1c029e38312
diff --git a/docs/images/agents/en/deerflow-mcp.md b/docs/images/agents/en/deerflow-mcp.mdnew file mode 100644index 000000000..722425736--- /dev/null+++ b/docs/images/agents/en/deerflow-mcp.md@@ -0,0 +1,73 @@+DeerFlow can connect to OpenViking through an MCP Server. MCP integration lets DeerFlow agents actively search, read, and use memories and knowledge from OpenViking while executing tasks.++## Step 1: Configure OpenViking credentials++Set the OpenViking MCP endpoint and API key in the environment that starts DeerFlow:++```bash+export OPENVIKING_MCP_URL="https://api.vikingdb.cn-beijing.volces.com/openviking/mcp"+export OPENVIKING_API_KEY="[TODO]your-api-key"+```++If DeerFlow uses a `.env` file, add the same variables there and confirm that the startup command loads it.++## Step 2: Create an MCP configuration file++Create an MCP configuration file in the DeerFlow project, for example `mcp.json`:++```json+{+ "mcpServers": {+ "openviking": {+ "url": "${OPENVIKING_MCP_URL}",+ "headers": {+ "Authorization": "Bearer ${OPENVIKING_API_KEY}"+ }+ }+ }+}+```++If DeerFlow already has a standard MCP config path, merge this server into the existing file.++## Step 3: Configure the OpenViking MCP Server++Enable this MCP Server in the DeerFlow agent or tool configuration, and keep the server name aligned with `openviking` in the MCP config file.++Allow DeerFlow to use OpenViking search, read, browse, and health-check tools to cover common memory retrieval and knowledge lookup scenarios.++## Step 4: Restart DeerFlow++Save the MCP configuration and restart DeerFlow:++```bash+pnpm dev+```++After restart, check the logs and confirm that the `openviking` MCP Server is loaded and its tools are available.++## Step 5: Verify MCP tools++Ask DeerFlow to check the OpenViking service status:++```text+Use the OpenViking MCP tools to check whether the current service is available.+```++You can also ask DeerFlow to search for an existing memory or resource:++```text+Search OpenViking for memories related to the current project.+```++If the agent can call OpenViking MCP tools and return results, MCP integration is working.++## Troubleshooting++| Symptom | Fix |+|---------|-----|+| MCP Server is not loaded | Check whether DeerFlow reads the MCP config path and whether the server name is configured consistently |+| Connection fails or times out | Confirm the runtime can access `api.vikingdb.cn-beijing.volces.com`; configure proxy or network allowlists if needed |+| OpenViking returns 401 / 403 | Verify `OPENVIKING_API_KEY` and make sure the request header is `Authorization: Bearer <API Key>` |+| Agent does not call tools | Explicitly allow OpenViking MCP tool usage in the DeerFlow system prompt or tool policy |+| Search results are empty | Confirm OpenViking already has related memories or knowledge resources, and try broader search keywords |diff --git a/docs/images/agents/en/deerflow-memory-manager.md b/docs/images/agents/en/deerflow-memory-manager.mdnew file mode 100644index 000000000..021756c60--- /dev/null+++ b/docs/images/agents/en/deerflow-memory-manager.md@@ -0,0 +1,79 @@+DeerFlow can use OpenViking as a long-term memory backend through MemoryManager. After the integration is enabled, DeerFlow writes conversation messages to OpenViking, recalls relevant memories before model calls, and injects them into the context.++## Step 1: Configure OpenViking credentials++Set the OpenViking base URL and API key in the environment that starts DeerFlow:++```bash+export OPENVIKING_BASE_URL="https://api.vikingdb.cn-beijing.volces.com/openviking"+export OPENVIKING_API_KEY="[TODO]your-api-key"+```++If you use `.env` or a deployment platform to manage environment variables, add the same variables there and make sure the DeerFlow process can read them at startup.++## Step 2: Update DeerFlow memory configuration++Enable MemoryManager in the DeerFlow configuration and point the provider to OpenViking:++```yaml+memory:+ enabled: true+ provider: openviking+ openviking:+ base_url: ${OPENVIKING_BASE_URL}+ api_key: ${OPENVIKING_API_KEY}+ auto_write: true+ auto_recall: true+ inject_recalled_memory: true+```++Enable write, recall, and injection together so DeerFlow can persist long-term memory during conversations and reuse relevant memories in later tasks.++## Step 3: Restart DeerFlow++Save the configuration and restart DeerFlow:++```bash+pnpm dev+```++If DeerFlow is deployed through Docker, a process manager, or a cloud service, use the corresponding restart flow and verify that the new environment variables are available at runtime.++## Step 4: Verify OpenViking connectivity++After startup, check the DeerFlow logs and confirm that MemoryManager initializes successfully without OpenViking authentication or network errors.++You can also check OpenViking connectivity directly:++```bash+curl -H "Authorization: Bearer ${OPENVIKING_API_KEY}" \+ "${OPENVIKING_BASE_URL}/health"+```++A service status response means OpenViking is reachable.++## Step 5: Verify memory write and recall++Start a DeerFlow conversation with a stable fact, for example:++```text+Remember that my DeerFlow test project uses OpenViking as the long-term memory backend.+```++Then start a new conversation and ask:++```text+What does my DeerFlow test project use as the long-term memory backend?+```++If DeerFlow answers OpenViking, memory write, recall, and context injection are working.++## Troubleshooting++| Symptom | Fix |+|---------|-----|+| MemoryManager fails to initialize | Check `memory.enabled`, `provider`, and whether DeerFlow is loading the expected configuration file |+| OpenViking returns 401 / 403 | Verify `OPENVIKING_API_KEY`, confirm it has not expired, and make sure requests use the `Bearer` prefix |+| Memories are not written | Confirm `auto_write` is enabled and check DeerFlow logs for write failures |+| Memories are not recalled | Confirm `auto_recall` and `inject_recalled_memory` are enabled and OpenViking already has related memories |+| Works locally but not after deployment | Check whether `OPENVIKING_BASE_URL` and `OPENVIKING_API_KEY` are injected into the deployed runtime |diff --git a/docs/images/agents/en/index.json b/docs/images/agents/en/index.jsonindex 97b133827..4ab8c8ff9 100644--- a/docs/images/agents/en/index.json+++ b/docs/images/agents/en/index.json@@ -1,6 +1,6 @@{"version": 1,- "updatedAt": "2026-06-02",+ "updatedAt": "2026-08-12","cdnBaseUrl": "https://docs.openviking.net/","accessMethods": [{@@ -95,6 +95,26 @@"logo": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_sth/ljhwZthlaukjlkulzlp/agent_logo/OpenCode.png","summary": "Provides one unified OpenCode plugin for repository context, memory tools, session sync, and automatic recall.","detailPath": "https://docs.openviking.net/agents/en/opencode.md"+ },+ {+ "id": "deerflow",+ "name": "DeerFlow",+ "tags": ["MemoryManager", "MCP"],+ "logo": "https://raw.githubusercontent.com/bytedance/deer-flow/main/frontend/public/images/deer.svg",+ "summary": "DeerFlow can connect through MemoryManager and MCP to automatically write, recall, inject, and manage memory. Enable both methods for the full memory experience.",+ "detailPath": "https://docs.openviking.net/agents/en/deerflow-memory-manager.md",+ "tabs": [+ {+ "id": "memory-manager",+ "label": "MemoryManager Integration",+ "detailPath": "https://docs.openviking.net/agents/en/deerflow-memory-manager.md"+ },+ {+ "id": "mcp",+ "label": "MCP Integration",+ "detailPath": "https://docs.openviking.net/agents/en/deerflow-mcp.md"+ }+ ]}]}diff --git a/docs/images/agents/zh/deerflow-mcp.md b/docs/images/agents/zh/deerflow-mcp.mdnew file mode 100644index 000000000..5364429cc--- /dev/null+++ b/docs/images/agents/zh/deerflow-mcp.md@@ -0,0 +1,73 @@+DeerFlow 支持通过 MCP Server 接入 OpenViking。MCP 接入的核心价值是打通知识检索能力,让 DeerFlow Agent 能够在任务执行过程中主动搜索、读取和使用 OpenViking 中的记忆与知识。++## 步骤 1:配置 OpenViking 鉴权信息++在启动 DeerFlow 的环境中配置 OpenViking MCP 服务地址和 API Key:++```bash+export OPENVIKING_MCP_URL="https://api.vikingdb.cn-beijing.volces.com/openviking/mcp"+export OPENVIKING_API_KEY="[TODO]your-api-key"+```++如果 DeerFlow 使用 `.env` 文件,请写入同名变量,并确认启动命令会加载该文件。++## 步骤 2:创建 MCP 配置文件++在 DeerFlow 项目中创建 MCP 配置文件,例如 `mcp.json`:++```json+{+ "mcpServers": {+ "openviking": {+ "url": "${OPENVIKING_MCP_URL}",+ "headers": {+ "Authorization": "Bearer ${OPENVIKING_API_KEY}"+ }+ }+ }+}+```++如果 DeerFlow 的 MCP 配置文件路径已有约定,请将以上配置合并到现有文件中。++## 步骤 3:配置 OpenViking MCP Server++在 DeerFlow 的 Agent 或工具配置中启用该 MCP Server,并确保 server 名称与 MCP 配置文件中的 `openviking` 保持一致。++建议允许 DeerFlow 使用 OpenViking 的搜索、读取、目录浏览和健康检查工具,以覆盖常见的记忆检索与知识读取场景。++## 步骤 4:重启 DeerFlow++保存 MCP 配置后重启 DeerFlow:++```bash+pnpm dev+```++重启后检查日志,确认 `openviking` MCP Server 已成功加载,且工具列表可以正常获取。++## 步骤 5:验证 MCP 工具是否可用++在 DeerFlow 中发起任务,让 Agent 主动检查 OpenViking 连接状态:++```text+请使用 OpenViking MCP 工具检查当前服务是否可用。+```++也可以让 DeerFlow 搜索一条已存在的记忆或资源:++```text+请从 OpenViking 中搜索和当前项目相关的记忆。+```++如果 Agent 能够调用 OpenViking MCP 工具并返回结果,说明 MCP 接入成功。++## 故障排查++| 现象 | 处理方式 |+|------|----------|+| MCP Server 未加载 | 检查 MCP 配置文件路径是否被 DeerFlow 读取,server 名称是否配置一致 |+| 连接失败或超时 | 确认网络可访问 `api.vikingdb.cn-beijing.volces.com`,必要时配置代理或网络白名单 |+| OpenViking 返回 401 / 403 | 检查 `OPENVIKING_API_KEY` 是否正确、是否过期,以及请求头是否为 `Authorization: Bearer <API Key>` |+| Agent 不主动调用工具 | 在 DeerFlow 的系统提示词或工具策略中明确允许使用 OpenViking MCP 工具 |+| 搜索结果为空 | 确认 OpenViking 中已有相关记忆或知识资源,并尝试放宽搜索关键词 |diff --git a/docs/images/agents/zh/deerflow-memory-manager.md b/docs/images/agents/zh/deerflow-memory-manager.mdnew file mode 100644index 000000000..b26990c0e--- /dev/null+++ b/docs/images/agents/zh/deerflow-memory-manager.md@@ -0,0 +1,79 @@+DeerFlow 支持通过 MemoryManager 接入 OpenViking 作为长期记忆后端。接入后,DeerFlow 会将对话消息写入 OpenViking,并在模型调用前通过 OpenViking 进行记忆召回,再注入到上下文中。++## 步骤 1:配置 OpenViking 鉴权信息++在启动 DeerFlow 的环境中配置 OpenViking 服务地址和 API Key:++```bash+export OPENVIKING_BASE_URL="https://api.vikingdb.cn-beijing.volces.com/openviking"+export OPENVIKING_API_KEY="[TODO]your-api-key"+```++如果使用 `.env` 或部署平台的环境变量管理能力,请写入同名变量,并确认 DeerFlow 进程启动时能够读取到。++## 步骤 2:修改 DeerFlow 的 memory 配置++在 DeerFlow 的配置文件中启用 MemoryManager,并将 provider 指向 OpenViking:++```yaml+memory:+ enabled: true+ provider: openviking+ openviking:+ base_url: ${OPENVIKING_BASE_URL}+ api_key: ${OPENVIKING_API_KEY}+ auto_write: true+ auto_recall: true+ inject_recalled_memory: true+```++建议同时开启写入、召回和注入,确保 DeerFlow 能够在对话过程中持续沉淀长期记忆,并在后续任务中自动使用相关记忆。++## 步骤 3:重启 DeerFlow++保存配置后重启 DeerFlow,使新的 memory 配置生效:++```bash+pnpm dev+```++如果你通过 Docker、进程管理器或云服务部署 DeerFlow,请使用对应的重启方式,并确认新的环境变量已注入到运行时。++## 步骤 4:验证 OpenViking 是否接入成功++启动后检查 DeerFlow 日志,确认 MemoryManager 初始化成功,且没有出现 OpenViking 鉴权或网络错误。++也可以直接检查 OpenViking 服务连通性:++```bash+curl -H "Authorization: Bearer ${OPENVIKING_API_KEY}" \+ "${OPENVIKING_BASE_URL}/health"+```++返回服务状态信息即表示 OpenViking 服务可访问。++## 步骤 5:验证记忆写入与召回是否正常++在 DeerFlow 中发起一轮包含稳定事实的对话,例如:++```text+请记住:我的 DeerFlow 测试项目使用 OpenViking 作为长期记忆后端。+```++随后开启一轮新对话并询问:++```text+我的 DeerFlow 测试项目使用什么作为长期记忆后端?+```++如果 DeerFlow 能够回答 OpenViking,说明记忆写入、召回和上下文注入链路已经生效。++## 故障排查++| 现象 | 处理方式 |+|------|----------|+| MemoryManager 初始化失败 | 检查 `memory.enabled`、`provider` 和 OpenViking 配置项是否已写入 DeerFlow 实际加载的配置文件 |+| OpenViking 返回 401 / 403 | 检查 `OPENVIKING_API_KEY` 是否正确、是否过期,以及请求头是否带有 `Bearer` 前缀 |+| 记忆没有写入 | 确认 `auto_write` 已开启,并检查 DeerFlow 日志中是否有写入失败信息 |+| 记忆无法召回 | 确认 `auto_recall` 和 `inject_recalled_memory` 已开启,并确保 OpenViking 中已有相关记忆 |+| 本地可用、部署后不可用 | 检查部署环境是否正确注入 `OPENVIKING_BASE_URL` 和 `OPENVIKING_API_KEY` |diff --git a/docs/images/agents/zh/index.json b/docs/images/agents/zh/index.jsonindex 486166702..4c533d5ff 100644--- a/docs/images/agents/zh/index.json+++ b/docs/images/agents/zh/index.json@@ -1,6 +1,6 @@{"version": 1,- "updatedAt": "2026-06-05",+ "updatedAt": "2026-08-12","cdnBaseUrl": "https://docs.openviking.net/","accessMethods": [{@@ -95,6 +95,26 @@"logo": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lm_sth/ljhwZthlaukjlkulzlp/agent_logo/OpenCode.png","summary": "提供一个统一 OpenCode 插件,支持仓库上下文、记忆工具、session 同步与自动 recall","detailPath": "https://docs.openviking.net/agents/zh/opencode.md"+ },+ {+ "id": "deerflow",+ "name": "DeerFlow",+ "tags": ["MemoryManager", "MCP"],+ "logo": "https://raw.githubusercontent.com/bytedance/deer-flow/main/frontend/public/images/deer.svg",+ "summary": "DeerFlow 支持通过 MemoryManager 和 MCP 接入,实现记忆的自动写入、召回、注入及管理。建议同时启用两种方式,以获得完整的记忆体验。",+ "detailPath": "https://docs.openviking.net/agents/zh/deerflow-memory-manager.md",+ "tabs": [+ {+ "id": "memory-manager",+ "label": "MemoryManager 接入",+ "detailPath": "https://docs.openviking.net/agents/zh/deerflow-memory-manager.md"+ },+ {+ "id": "mcp",+ "label": "MCP 接入",+ "detailPath": "https://docs.openviking.net/agents/zh/deerflow-mcp.md"+ }+ ]}]}