WrenAI Agent工作流
AI Skill Hub 强烈推荐：WrenAI Agent工作流 是一款优质的AI工具。在 GitHub 上收获超过 15.2k 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AI工具解决方案，这是一个值得深入了解的选择。
📚 深度解析
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
WrenAI Agent工作流 依赖 Rust 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 Rust 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 WrenAI Agent工作流 的版本更新，及时通知重要功能变化。
📋 工具概览
WrenAI Agent工作流 是一款基于 Rust 开发的开源工具，专注于 工作流、AI代理、SQL生成 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
📖 中文文档
WrenAI Agent工作流 是一款基于 Rust 开发的开源工具，专注于 工作流、AI代理、SQL生成 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：cargo install（推荐） cargo install wrenai # 方式二：从源码编译 git clone https://github.com/Canner/WrenAI cd WrenAI cargo build --release # 二进制在 ./target/release/wrenai
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 查看帮助 wrenai --help # 基本运行 wrenai [options] <input> # 详细使用说明请查阅文档 # https://github.com/Canner/WrenAI
# wrenai 配置说明 # 查看配置选项 wrenai --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 WRENAI_CONFIG="/path/to/config.yml"
简介
What's Included
- Modeling Definition Language (MDL) — the semantic layer: models, columns, relationships, views, cubes, metrics
- Engine: Apache DataFusion based, 22+ data sources (BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks, DuckDB, and more)
- GenBI dashboards: agent-built, browser-side apps powered by
wren-core-wasm, deployable to Vercel / Cloudflare Pages - Knowledge & memory — the AI context layer: business meaning in version-controlled
instructions.mdandqueries.yml, plus a local LanceDB memory index (hybrid retrieval) for recall - Agent SDK:
wren-langchain(LangChain / LangGraph),wren-pydantic; reference Python integration for other stacks - Governed execution primitives: functions, dry-plan, row limits, structured errors
What's next
- End-to-end correctness primitives: value profiling, rich retrieval, structured errors, golden eval runner
- Agent-native distribution: first-class SDKs across major agent frameworks; see GitHub Discussions for what's prioritized next
Full roadmap and design notes: see the introduction.
GenBI in three beats: Generate · Deploy · Know
- Generate. Your agent turns a business question into governed text-to-SQL and charts. Schema-aware retrieval, MDL planning, dry-plan validation, and structured errors keep it correct instead of confidently wrong.
- Deploy. Turn any answer into a shareable, browser-side dashboard powered by
wren-core-wasmand ship it to your own Vercel or Cloudflare Pages account with one command. - Know. The knowledge that makes all of this correct lives in versionable, evidence-linked files: semantic models (MDL), company definitions (
instructions.md), and a memory of what worked. Reviewable. Git-friendly. Never locked inside someone else's UI.
Why agent builders pick WrenAI
- Generative BI, end to end. Wren does governed text-to-SQL — and goes beyond it: generate the answer, deploy the dashboard, share the URL, all driven by the agents you already use.
- Knowledge management built in. Business meaning, approved definitions, and proven examples are captured as a reviewable, version-controlled semantic layer (MDL), not buried in prompts.
- Open by default. Open-sourced core, SDK, and skills under the Apache-2.0 license.
- Correctness as primitives. Rich schema retrieval, dry-plan validation, structured errors with hints, value profiling, eval runner. The agent orchestrates; the trace lives in its reasoning.
- Governed execution, reviewable context. Dry-plan validation, row limits, and structured errors keep agent-generated SQL inside guardrails, and every definition and example lives in Git — reviewable, versioned, diff-able. (Row/column-level security and access control are Cloud / self-hosted — see Open core: OSS vs. Cloud / self-hosted.)
- Sits on top of your existing stack. Warehouse, transformation pipelines, your existing semantic layer. Not another tool to maintain.
1. Install the CLI
pip install wrenai # core (DuckDB included)
pip install "wrenai[postgres,memory]" # add per-datasource and memory extras as neededTip for users in mainland China: Ifpip installis slow or fails, use the Tsinghua mirror:If HuggingFace model downloads time out, add> pip install wrenai -i https://pypi.tuna.tsinghua.edu.cn/simple >export HF_ENDPOINT=https://hf-mirror.combefore running the CLI.
2. Install the discovery stub for your AI client
npx skills add Canner/WrenAI # auto-detects Claude Code, Cursor, Cline, Codex, …The stub is ~50 lines. It teaches your agent to fetch workflow guides via wren skills get <name> and shaped prompts via wren ask "<question>" --guided|--direct, and everything else lives in the CLI.
6. Build & deploy a dashboard: the *Deploy* beat
"Turn that into an interactive dashboard I can filter and share, and deploy it to Vercel."
The agent runs wren skills get genbi, builds a browser-side GenBI app from your project's context, previews it locally, and ships it to your own Vercel or Cloudflare Pages account, returning a live, shareable URL. See the Build & deploy a GenBI app guide.
Want to try it without your own database? Ask your agent to use the bundled jaffle_shop sample dataset. Same flow, querying a real warehouse end-to-end in a couple of minutes.
Quickstart
WrenAI is agent-driven by design: install the CLI, install a one-file discovery stub for your AI client, then let your AI agent drive the rest. Workflow guides live inside the CLI itself and are served on demand, so content always matches the installed version.
4. (Optional) Enrich the project: the *Know* beat
Once onboarding finishes, ask:
"Enrich my Wren project with the business context in raw/."
The agent runs wren skills get enrich-context and follows the guide in grill mode (one question at a time) or auto-pilot mode (agent reads <project>/raw/ and proposes). Both modes write to MDL, instructions, queries, and memory, all reviewable, all Git-friendly.
How Wren compares
| A raw LLM agent | A traditional BI tool | A bare semantic layer | **WrenAI** | |
|---|---|---|---|---|
| Writes SQL for you | ✅ (often wrong) | ❌ | ❌ | ✅ governed |
| Knows your business definitions | ❌ | partial, in-tool | ✅ (schema only) | ✅ + non-schema knowledge |
| Generates & deploys dashboards | ❌ | ✅ (manual, in-tool) | ❌ | ✅ agent-driven |
| Works through *your* agents (Claude Code, Cursor, MCP…) | ✅ | ❌ | ❌ | ✅ |
| Open, reviewable, Git-friendly context | ❌ | ❌ | partial | ✅ |
| Governed execution across 22+ sources | ❌ | per-connector | ✅ (definitions only) | ✅ |
What's in OSS vs. Wren AI Cloud / self-hosted?
The open-source engine in this repo — MDL semantic layer, governed text-to-SQL, MCP server, CLI, and 22+ connectors — is free forever and self-hostable under Apache-2.0. Row- and column-level security, access control with users and groups, the GenBI UI and dashboards, GenBI Apps, agentic mode, context preparation, and support/SLAs are commercial, delivered as Wren AI Cloud or self-hosted Enterprise Plus. The boundary is published: Open core — what's OSS vs. commercial.
Open core: OSS vs. Cloud / self-hosted
Wren AI is open core. The context engine in this repo — MDL semantic layer, governed text-to-SQL, MCP server, CLI, and 22+ connectors — is open source under Apache-2.0, free forever, and self-hostable. It runs without us.
The following are commercial, delivered as Wren AI Cloud or self-hosted Enterprise Plus:
- Row- and column-level security (RLS / CLS) and access control with users & groups
- GenBI UI, dashboards, embedded & APIs
- Scenario AI harnesses — GenBI Apps, Agentic Mode, AI-assisted context preparation
- Advanced security & audit, support & SLAs, plus cloud / VPC / air-gapped deployment
Same engine underneath, and your MDL stays in your git either way. The full boundary is published — see Open core: what's OSS vs. commercial →.
5. Ask questions: the *Generate* beat
"Who are our top 10 customers by sales this quarter?"
Your agent fetches MDL context, recalls similar past queries, writes governed SQL, and executes via wren query.
FAQ
WrenAI 是一款专为 Agent 设计的生成式 BI（Generative BI）平台。它不仅实现了从自然语言到 SQL 的转换，更通过端到端的流程，让 AI Agent 能够直接生成受控的查询、构建可视化 Dashboard 并进行分享。WrenAI 旨在解决传统 Text-to-SQL 容易出现的“一本正经胡说八道”问题，通过引入语义层和知识管理，为开发者提供可靠、可解释的数据分析能力。
WrenAI 集成了强大的 Modeling Definition Language (MDL)，支持对模型、列、关系、视图及指标的精细化定义，并提供行级/列级访问控制（RLAC/CLAC）。其核心 Engine 基于 Apache DataFusion 构建，支持超过 22 种数据源。此外，通过 wren-core-wasm 技术，用户可以将生成的 GenBI dashboards 直接部署至 Vercel 或 Cloudflare Pages，实现轻量化的浏览器端应用分发。
WrenAI 采用“生成、部署、认知”的三步走策略。首先，通过 Agent 将业务问题转化为受控的 SQL 和图表；接着，利用 wren-core-wasm 技术将答案转化为可分享的浏览器端 Dashboard，并一键部署到 Vercel 或 Cloudflare Pages；最后，通过知识注入实现对业务上下文的深度理解，完成从数据到决策的闭环。
WrenAI 采用 Agent-driven 设计理念。开发者只需安装 CLI 工具，并为现有的 AI Client 安装一个单文件 Discovery Stub，即可让 AI Agent 接管后续的所有操作。为了确保文档与版本同步，所有的 Workflow 指南都直接内置在 CLI 内部，根据用户安装的版本按需实时提供服务。
在完成初始化后，用户可以通过“Enrich”模式增强项目。通过执行 `wren skills get enrich-context` 命令，Agent 可以进入 grill mode（逐问确认模式）或 auto-pilot mode（自动驾驶模式）。在 auto-pilot 模式下，Agent 会自动读取项目中的 `raw/` 目录并提出改进建议，所有变更都会写入 MDL、指令、查询和 Memory 中，且全程支持人工审核。
在实际使用中，用户可以直接向 Agent 提问，例如：“本季度销售额前 10 的客户是谁？”此时，Agent 会自动获取 MDL 上下文，检索并回忆相似的历史查询，编写符合规范的受控 SQL，并通过 `wren query` 执行，确保输出结果的准确性与业务逻辑的一致性。
高星开源项目，Rust编写性能优异。创新的SQL上下文层设计让AI安全访问数据库，治理能力强。适合企业级应用，但学习成本较高。
- 构建多智能体协作系统的 Agent 开发者
- 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）
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 构建多智能体协作系统的 Agent 开发者
- 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）
👥 适合人群
🎯 使用场景
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
⚖️ 优点与不足
- +GitHub 15.2k Star，社区高度认可
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
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，WrenAI Agent工作流 是一款质量优秀的AI工具，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 | WrenAI |
| 原始描述 | 开源AI工作流：The open context layer that gives AI agents grounded, governed SQL across 20+ da。⭐15.2k · Rust |
| Topics | 工作流AI代理SQL生成数据治理多数据源上下文工程 |
| GitHub | https://github.com/Canner/WrenAI |
| License | NOASSERTION |
| 语言 | Rust |
收录时间：2026-05-17 · 更新时间：2026-05-19 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。