WeKnora Agent工作流
AI Skill Hub 强烈推荐：WeKnora Agent工作流 是一款优质的Agent工作流。在 GitHub 上收获超过 14.9k 颗 Star，AI 综合评分 8.2 分，在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案，这是一个值得深入了解的选择。
📚 深度解析
WeKnora Agent工作流 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.2 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
WeKnora Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
📖 中文文档
WeKnora Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 方式一：go install（推荐） go install github.com/Tencent/WeKnora@latest # 方式二：从源码编译 git clone https://github.com/Tencent/WeKnora cd WeKnora go build -o weknora . # 方式三：下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/Tencent/WeKnora/releases
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 查看帮助 weknora --help # 基本运行 weknora [options] <input> # 详细使用说明请查阅文档 # https://github.com/Tencent/WeKnora
# weknora 配置说明 # 查看配置选项 weknora --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export WEKNORA_CONFIG="/path/to/config.yml"
简介
<p align="center"> <a href="https://weknora.weixin.qq.com"> <picture> <source media="(prefers-color-scheme: dark)" srcset="./docs/images/readme/hero-en-dark.svg"> <img src="./docs/images/readme/hero-en-light.svg" alt="WeKnora: find the answers, and put knowledge to work. Tencent's open-source knowledge management framework for Q&A, tasks and wikis." width="100%"> </picture> </a> </p>
<p align="center"> <a href="https://weknora.weixin.qq.com"><img alt="Website" src="https://img.shields.io/badge/website-weknora.weixin.qq.com-b8863b?style=flat-square&labelColor=101f38"></a> <a href="https://weknora.weixin.qq.com/docs/"><img alt="Docs" src="https://img.shields.io/badge/docs-read-b8863b?style=flat-square&labelColor=101f38"></a> <a href="./CHANGELOG.md"><img alt="Release" src="https://img.shields.io/badge/release-v0.8.3-b8863b?style=flat-square&labelColor=101f38"></a> <a href="./LICENSE"><img alt="License" src="https://img.shields.io/badge/license-MIT-b8863b?style=flat-square&labelColor=101f38"></a> <a href="https://github.com/Tencent/WeKnora/stargazers"><img alt="Stars" src="https://img.shields.io/github/stars/Tencent/WeKnora?style=flat-square&labelColor=101f38&color=b8863b"></a> <br/> <a href="https://chatbot.weixin.qq.com"><img alt="WeChat Dialog Open Platform" src="https://img.shields.io/badge/WeChat_Dialog-Open_Platform-07c160?style=flat-square&labelColor=101f38&logo=wechat&logoColor=white"></a> <a href="https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd"><img alt="Chrome Extension" src="https://img.shields.io/badge/Chrome-extension-4285f4?style=flat-square&labelColor=101f38&logo=googlechrome&logoColor=white"></a> <a href="https://clawhub.ai/lyingbug/weknora"><img alt="ClawHub Skill" src="https://img.shields.io/badge/ClawHub-skill-ff6b35?style=flat-square&labelColor=101f38"></a> <a href="https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora"><img alt="npm @wxg-prc-cpg/dsh-weknora" src="https://img.shields.io/npm/v/@wxg-prc-cpg/dsh-weknora?style=flat-square&label=dsh-weknora&labelColor=101f38&color=cb3837&logo=npm&logoColor=white"></a> </p>
<p align="center"> <b>English</b> · <a href="./README_CN.md">简体中文</a> · <a href="./README_JA.md">日本語</a> · <a href="./README_KO.md">한국어</a> </p>
<p align="center"> <a href="#overview">Overview</a> · <a href="#quick-start">Quick Start</a> · <a href="#whats-new">What's New</a> · <a href="#features">Features</a> · <a href="#clients-and-integrations">Clients</a> · <a href="#documentation">Docs</a> · <a href="#development">Development</a> </p>
<p align="center"> <a href="https://trendshift.io/repositories/15289"><img src="https://trendshift.io/api/badge/repositories/15289" alt="Tencent/WeKnora | Trendshift" width="220" height="48"/></a> </p>
Overview
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval and reasoning. It brings a team's documents together so they can be searched, reasoned over and kept up to date.
https://github.com/user-attachments/assets/5722b10d-d04d-49ed-a6cc-635a8c77d91f
<p align="center"><sub>1:52 · 1080p · No narration, English on-screen text</sub></p>
Use RAG to look things up, the agent for multi-step tasks, and the wiki to organize knowledge. All three work on the same knowledge bases.
<picture> <source media="(prefers-color-scheme: dark)" srcset="./docs/images/readme/capabilities-en-dark.svg"> <img src="./docs/images/readme/capabilities-en-light.svg" alt="01 RAG: answers you can check, with hybrid search, multimodal parsing and citations. 02 Agent: tasks done with knowledge and tools, with multi-step reasoning, skills and sandbox, the local browser, MCP tools and memory. 03 Wiki: documents organized into a wiki, with a knowledge graph and rollback." width="100%"> </picture>
The agent's toolbox. Skills installed from ClawHub / SkillHub / Git / ZIP run in session-persistent Docker / E2B / Cube sandboxes, with an interactive terminal and graphical desktop beside the chat. Through the BrowserSkill extension the agent operates the user's own Chrome or Edge, and external MCP services (OAuth included) can be connected and enabled tool by tool.
Beyond the three modes:
- Memory and curation: cross-session long-term memory keeps the profile, preferences and facts a user has confirmed. Folder uploads keep their directory tree, and retrieval chunks can be edited, diffed and rolled back.
- Data sources and formats: auto-sync from Feishu wiki / Feishu Drive / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / Seafile / RSS, with more on the way. 10+ document formats including PDF, Word, images, Excel and XMind; Office files are parsed in-process by anydoc.
- Channels and integrations: Q&A in WeCom, Feishu, Slack, Telegram and other IM apps; an embed widget for external websites; a built-in MCP Server for Cursor, Claude and other AI tools; scoped API keys with a principal model for programmatic access.
- Models: 29 built-in vendors with a generated model catalog, including OpenAI, DeepSeek, Qwen (Alibaba Cloud), Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, LiteLLM and Ollama.
- Permissions and operations: multi-workspace RBAC (four roles, per-resource ownership, per-workspace audit log), several storage instances per workspace, a runtime task-queue dashboard with worker-pool governance, and Langfuse tracing for agent steps, token usage and pipelines.
- Deployment: LLMs, vector databases and storage backends are all swappable. Deploy locally or on a private cloud and keep the data in your own environment.
What's New
Features
| Area | Highlights |
|---|---|
| [Q&A and agent](https://weknora.weixin.qq.com/docs/03-features/07-agent) | Quick Q&A answers from knowledge bases with citations; smart reasoning runs a ReAct agent over knowledge bases, web search, MCP tools, skills and the local browser. Steer, fork or rewind a running conversation, and keep [long-term memory](https://weknora.weixin.qq.com/docs/03-features/23-memory) across sessions |
| [Wiki](https://weknora.weixin.qq.com/docs/03-features/14-wiki) | Agent-generated, interlinked wiki pages with a knowledge graph; in-browser editing, revision diff and rollback |
| [Skills and sandbox](https://weknora.weixin.qq.com/docs/03-features/22-skills-sandbox) | Skill catalog installed from ClawHub / SkillHub / Git / ZIP; session-persistent Docker / E2B / Cube sandboxes with network policy; terminal and graphical desktop beside the chat |
| [Knowledge bases](https://weknora.weixin.qq.com/docs/03-features/02-knowledge-base) | FAQ, document and wiki bases; folder tree; chunk editing with revisions; per-upload parsing, chunking and multimodal settings; auto-tagging |
| [Retrieval](https://weknora.weixin.qq.com/docs/03-features/05-retrieval-engines) | Keyword + vector hybrid search, rerank, parent-child chunking and GraphRAG ([Neo4j](https://weknora.weixin.qq.com/docs/03-features/09-knowledge-graph)); end-to-end evaluation with recall and BLEU / ROUGE |
| [Access and security](https://weknora.weixin.qq.com/docs/03-features/01-tenant-auth) | Workspace RBAC with four roles and an audit log; scoped API keys; OIDC; AES-256-GCM credential encryption; SSRF-safe outbound requests with a whitelist-only mode |
| [Operations](https://weknora.weixin.qq.com/docs/03-features/16-observability) | Langfuse tracing for agent steps, tokens and pipelines; document parsing timeline; task-queue dashboard with worker pools; automatic migrations on upgrade |
Run with Docker Compose
Requires Docker, Docker Compose and Git.
git clone https://github.com/Tencent/WeKnora.git
cd WeKnora
cp .env.example .env # Edit .env as needed, see comments in the file
docker compose pull # Pull the latest images
docker compose up -d # Start core servicesThen open http://localhost and follow the onboarding guide. A walkthrough with sample data is in the Quickstart.
[!TIP] To use a local Ollama model, runollama serve > /dev/null 2>&1 &first. For the Ollama embedding model name,OLLAMA_BASE_URL, and RAM notes, see Configuration.
| Service | URL |
|---|---|
| Web UI | http://localhost |
| Backend API | http://localhost:8080 |
| Langfuse Tracing | http://localhost:3000 |
Other ways to deploy
| Option | When to use it |
|---|---|
| **Docker Compose** | The standard deployment above: all features, multiple services |
| **Kubernetes (Helm)** | Production clusters; the chart is in [helm/](./helm) |
| **Lite single binary** | Local or low-resource use with no external dependencies (SQLite + in-memory queue); see [Lite vs. standard](./docs/LITE.md) |
| **Desktop app** | The Lite runtime with a GUI, login-free start and a macOS host sandbox; no installer is published yet, so build it from source |
All options, hardware requirements and deployment topologies: Installation guide.
[!WARNING] WeKnora ships with login authentication, but for production deployments we strongly recommend that you: - deploy it in an internal / private network rather than on the public internet; - avoid exposing the service directly to public networks, to prevent information leakage; - configure proper firewall rules and access controls for the deployment environment; - regularly update to the latest version for security patches and improvements.
Quick Start
 ONLINE WeChat Dialog Open Platform Manage knowledge bases online and connect Q&A to Official Accounts, Mini Programs and other WeChat scenarios. Open the platform → |
CLOUD Tencent Cloud Lighthouse Deploy WeKnora from an application template and run it on your own cloud server. Deploy on Tencent Cloud → |
 SELF-HOSTED Your own environment Deploy with Docker or Kubernetes and configure models, storage and networking yourself. Run with Docker Compose ↓ |
Optional services
Add --profile flags to enable additional components; multiple profiles can be combined.
| Profile | Adds |
|---|---|
| _(default)_ | Core services |
full | All features |
neo4j | Knowledge Graph (Neo4j) |
minio | Object Storage (MinIO) |
langfuse | Tracing (Langfuse) |
docker compose --profile neo4j --profile minio pull
docker compose --profile neo4j --profile minio up -d
docker compose down # Stop servicesSet WEKNORA_VERSION in .env to the target release (e.g. 0.8.3), or keep latest
docker compose pull # Pull images matching WEKNORA_VERSION docker compose up -d # Recreate containers with new images ```
[!NOTE] docker compose up -d alone reuses locally cached images and may leave the UI version out of sync with the release you downloaded. Read the upgrade notes before upgrading. Deployments older than v0.8.2 should also read the v0.8.2 notes.
Command-Line Interface
weknora is the official CLI for driving the API from a terminal or an AI agent. It is agent-first: every command emits a stable JSON envelope by default (with typed error codes mapped to exit codes), and --format text renders for humans. It also serves a curated MCP tool surface (weknora mcp serve) and ships bundled Agent Skills.
weknora profile add prod --host https://kb.example.com --use
weknora auth login
weknora kb list
weknora link --kb my-knowledge-base # bind the current directory
weknora doc upload notes.md
weknora chat "summarise the design doc"For headless / CI use, set WEKNORA_API_KEY + WEKNORA_HOST and skip auth login; no credentials are written to disk. See cli/README.md for install + 5-minute quickstart and cli/AGENTS.md for the operational contract AI agents rely on.
Clients and Integrations
| Client | What it does | |
|---|---|---|
| <img src="./docs/images/readme/icons/terminal.svg" width="22" height="22" alt=""> | [**CLI weknora**](./cli/README.md) | Agent-first command line for the full API, with a curated MCP tool surface and bundled Agent Skills |
| <img src="./docs/images/readme/icons/plug.svg" width="22" height="22" alt=""> | [**Built-in MCP Server**](https://weknora.weixin.qq.com/docs/03-features/08-mcp) | Publishes knowledge bases to Cursor, Claude and other MCP clients over Streamable HTTP; the Python [mcp-server/](./mcp-server/MCP_CONFIG.md) is deprecated |
| <img src="./website-docs/homepage/public/docs/_home/brands/browserskill.png" width="22" height="22" alt=""> | [**Local Browser (BrowserSkill)**](https://weknora.weixin.qq.com/docs/05-clients/09-local-browser) | Lets agents operate the user's own Chrome / Edge |
| <img src="./website-docs/homepage/public/docs/_home/brands/chrome.svg" width="22" height="22" alt=""> | [**Chrome Extension**](https://chromewebstore.google.com/detail/jpemjbopikggjlmikmclgbmkhhopjdgd) | Select text, images, or entire pages in the browser and save them as knowledge entries with one click, without copy-paste or file upload |
| <img src="./docs/images/readme/icons/phone.svg" width="22" height="22" alt=""> | [**WeChat Mini Program**](./miniprogram/README.md) | Lightweight mobile client: configure API access, select knowledge bases, import URLs, and ask knowledge chat from WeChat |
| <img src="./docs/images/readme/icons/skills.svg" width="22" height="22" alt=""> | [**ClawHub Skill**](https://clawhub.ai/lyingbug/weknora) | A WeKnora skill on ClawHub for document import, hybrid search and knowledge management via the REST API |
| <img src="./website-docs/homepage/public/docs/_home/brands/deepseek-color.svg" width="22" height="22" alt=""> | [**DeepSeek Harness plugin**](https://www.npmjs.com/package/@wxg-prc-cpg/dsh-weknora) | Gives dsh coding agents four read-only tools: search, read document, ask and list knowledge bases |
| <img src="./docs/images/readme/icons/code.svg" width="22" height="22" alt=""> | [**Website Embed Widget**](https://weknora.weixin.qq.com/docs/03-features/13-embed-channel) | Publishes agents on external sites |
| <img src="./docs/images/readme/icons/braces.svg" width="22" height="22" alt=""> | [**Go SDK**](https://weknora.weixin.qq.com/docs/05-clients/03-go-sdk) | CRUD for knowledge bases, documents and sessions, plus SSE streaming Q&A |
| <img src="./website-docs/homepage/public/docs/_home/brands/wechat-dialog.png" width="22" height="22" alt=""> | [**WeChat Dialog Open Platform**](https://chatbot.weixin.qq.com) | Hosted Q&A built on WeKnora: upload knowledge and publish a Q&A service in WeChat without writing code |
Quick Q&A and smart reasoning
Two ways to ask. Quick Q&A answers from the knowledge base with RAG and cites the sources it used. In smart reasoning the agent plans multi-step work, searching, reading documents and calling tools and skills, and shows each step in the conversation. Docs →
<a href="./docs/images/readme/spotlight-qa-light.webp"> <picture> <source media="(prefers-color-scheme: dark)" srcset="./docs/images/readme/spotlight-qa-dark.webp"> <img src="./docs/images/readme/spotlight-qa-light.webp" alt="Quick Q&A and smart reasoning" width="100%"> </picture> </a>
WeKnora 是一个开源的、由大语言模型（LLM）驱动的知识框架，专为企业级文档理解、语义检索及自主推理而设计。它集成了三种核心能力：基于 RAG 的快速问答（Quick Q&A）用于日常信息查询；具备 ReAct Agent 能力的智能体，能够自主编排检索、MCP 工具及 Web Search 来处理复杂的跨步骤任务；以及能够自动生成结构化、互联 Markdown 文档的 Wiki 模式。
WeKnora 提供多样化的智能交互能力：通过 Intelligent Reasoning 实现基于 ReAct 框架的多步推理，支持自定义 Agent 并自主调用 MCP 工具与 Web Search；Quick Q&A 模式利用 RAG 技术实现对知识库的高效、准确问答；Wiki Mode 则能通过 Agent 驱动，自动将碎片化信息转化为结构化的知识百科。
在开始部署 WeKnora 之前，请确保您的开发环境已安装 Git 以及 Docker 与 Docker Compose，以便通过容器化技术快速构建运行环境。
您可以通过 Git 克隆仓库并使用 Docker Compose 进行部署。首先执行 `git clone` 获取源码，复制 `.env.example` 为 `.env` 并根据注释修改配置。随后运行 `docker compose up -d` 启动核心服务。若需使用本地 Ollama 模型，请先运行 `ollama serve`。此外，您可以通过 `--profile` 参数启用 full、neo4j 或 minio 等可选服务组件。
项目启动后，请访问 http://localhost 进入 Web 界面进行交互。开发者可以通过官方提供的 `weknora` CLI 工具在终端或 AI Agent 中驱动 API，其命令设计遵循 `gh` CLI 的 `<noun> <verb>` 规范，并支持通过 `--json` 参数输出稳定的 JSON 格式数据。
WeKnora 提供直观的智能问答界面与 Wiki 浏览器功能。开发者可以通过官方 API 进行深度集成，详细的 API 文档请参考 `./docs/api/README.md`。此外，项目还提供了命令行接口（CLI）以支持自动化操作与 AI Agent 的调用。
WeKnora 配备了专用的 Chrome Extension 插件，允许用户直接将网页内容捕获到 WeKnora 知识库中。通过在浏览器中选择文本、图片或整个页面，用户可以实现一键保存为知识条目，彻底告别繁琐的复制粘贴操作。
Go语言实现，性能优异。RAG工作流完整，文档知识库转换能力强。生态活跃，14.9k星标表明社区认可度高。
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 构建企业知识库 / RAG 检索应用的团队
- 跨境业务、多语言内容运营团队
- 做语音类 AI 产品的开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
- 本地部署优先选 GGUF 量化模型，节省显存并保持响应速度
- 分块大小建议 256-512 tokens，向量库优选 pgvector 或 Qdrant
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- 容器内无法访问宿主机 localhost — 使用 host.docker.internal
- embedding 模型与查询模型不一致导致检索失效
- 显存不足直接 OOM — 优先降低 context 或换更小的量化模型
- Docker：WeKnora 提供官方镜像，docker compose up 一键启动
- CLI：直接 npm install -g / pip install，命令行调用
- 本地部署：CPU 8GB 起，GPU 推荐 16GB+ 显存
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 构建企业知识库 / RAG 检索应用的团队
- 跨境业务、多语言内容运营团队
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
- 本地部署优先选 GGUF 量化模型，节省显存并保持响应速度
- 分块大小建议 256-512 tokens，向量库优选 pgvector 或 Qdrant
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- 容器内无法访问宿主机 localhost — 使用 host.docker.internal
- embedding 模型与查询模型不一致导致检索失效
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +GitHub 14.9k Star，社区高度认可
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
该工具使用 NOASSERTION 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
🔗 相关工具推荐
❓ 常见问题 FAQ
总体来看，WeKnora Agent工作流 是一款质量优秀的Agent工作流，在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态，建议收藏备用，结合自身场景选择合适时机引入使用。
| 原始名称 | WeKnora |
| 原始描述 | 开源AI工作流：Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an 。⭐14.9k · Go |
| Topics | RAG知识库LLM工作流Go开发 |
| GitHub | https://github.com/Tencent/WeKnora |
| License | NOASSERTION |
| 语言 | Go |
收录时间：2026-05-14 · 更新时间：2026-05-16 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。