{"id":13901284,"url":"https://github.com/Canner/WrenAI","last_synced_at":"2025-07-17T21:32:56.564Z","repository":{"id":232364466,"uuid":"771350543","full_name":"Canner/WrenAI","owner":"Canner","description":"🚀 Open-source SQL AI Agent for Text-to-SQL. Supporting PostgreSQL, DuckDB, MySQL, MS SQL, ClickHouse, Trino, JSON, CSV, Parquet data sources, and more! 🚀","archived":false,"fork":false,"pushed_at":"2024-10-29T11:22:18.000Z","size":9506,"stargazers_count":1971,"open_issues_count":54,"forks_count":202,"subscribers_count":24,"default_branch":"main","last_synced_at":"2024-10-29T11:46:08.899Z","etag":null,"topics":["agent","ai","bigquery","duckdb","fastapi","gpt","hacktoberfest","llm","nextjs","nlp","openai","postgresql","python","rag","sql","sqlai","text-to-sql","text2sql","typescript"],"latest_commit_sha":null,"homepage":"https://getwren.ai/oss","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Canner.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-03-13T06:18:20.000Z","updated_at":"2024-10-29T00:36:52.000Z","dependencies_parsed_at":"2024-11-05T12:53:51.245Z","dependency_job_id":null,"html_url":"https://github.com/Canner/WrenAI","commit_stats":{"total_commits":606,"total_committers":22,"mean_commits":"27.545454545454547","dds":0.8135313531353136,"last_synced_commit":"4cb5163d98de23221decb930738c12ad9f8de82d"},"previous_names":["canner/wrenai"],"tags_count":104,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Canner%2FWrenAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Canner%2FWrenAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Canner%2FWrenAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Canner%2FWrenAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Canner","download_url":"https://codeload.github.com/Canner/WrenAI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226305296,"owners_count":17603788,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","ai","bigquery","duckdb","fastapi","gpt","hacktoberfest","llm","nextjs","nlp","openai","postgresql","python","rag","sql","sqlai","text-to-sql","text2sql","typescript"],"created_at":"2024-08-06T21:01:08.267Z","updated_at":"2024-11-25T09:31:09.021Z","avatar_url":"https://github.com/Canner.png","language":"TypeScript","readme":"\n\n\u003cp align=\"center\" id=\"top\"\u003e\n  \u003ca href=\"https://getwren.ai/?utm_source=github\u0026utm_medium=title\u0026utm_campaign=readme\"\u003e\n    \u003cpicture\u003e\n      \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"./misc/wrenai_logo.png\"\u003e\n      \u003cimg src=\"./misc/wrenai_logo_white.png\" width=\"300px\"\u003e\n    \u003c/picture\u003e\n    \u003ch1 align=\"center\"\u003eWren AI\u003c/h1\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca aria-label=\"Follow us on X\" href=\"https://x.com/getwrenai\"\u003e\n    \u003cimg alt=\"\" src=\"https://img.shields.io/badge/-@getwrenai-blue?style=for-the-badge\u0026logo=x\u0026logoColor=white\u0026labelColor=gray\u0026logoWidth=20\"\u003e\n  \u003c/a\u003e\n  \u003ca aria-label=\"Releases\" href=\"https://github.com/canner/WrenAI/releases\"\u003e\n    \u003cimg alt=\"\" src=\"https://img.shields.io/github/v/release/canner/WrenAI?logo=github\u0026label=GitHub%20Release\u0026color=blue\u0026style=for-the-badge\"\u003e\n  \u003c/a\u003e\n  \u003ca aria-label=\"License\" href=\"https://github.com/Canner/WrenAI/blob/main/LICENSE\"\u003e\n    \u003cimg alt=\"\" src=\"https://img.shields.io/github/license/canner/WrenAI?color=blue\u0026style=for-the-badge\"\u003e\n  \u003c/a\u003e\n  \u003ca aria-label=\"Join the community on GitHub\" href=\"https://discord.gg/5DvshJqG8Z\"\u003e\n    \u003cimg alt=\"\" src=\"https://img.shields.io/badge/-JOIN%20THE%20COMMUNITY-blue?style=for-the-badge\u0026logo=discord\u0026logoColor=white\u0026labelColor=grey\u0026logoWidth=20\"\u003e\n  \u003c/a\u003e\n  \u003ca aria-label=\"Canner\" href=\"https://cannerdata.com/?utm_source=github\u0026utm_medium=badge\u0026utm_campaign=readme\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/%F0%9F%A7%A1-Made%20by%20Canner-blue?style=for-the-badge\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003e Wren AI is an **open-source SQL AI Agent** that empowers data, product, and business teams to access insights through chat, built-in well designed intuitive UI and UX, integrating seamlessly with tools like Excel and Google Sheets.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./misc/wrenai_view.png\"\u003e\n\u003c/p\u003e\n\n## 🕶 Try it yourself!\n\nhttps://github.com/user-attachments/assets/737bbf1f-f9f0-483b-afb3-2c622c9b91ba\n\n👉 Try with your data on [Wren AI Cloud](https://getwren.ai/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme) or [Install in your local environment](https://docs.getwren.ai/oss/installation/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme)\n\n\n## 🎯 Our Vision \u0026 Mission\n\nWren AI’s mission is to democratize data by bringing AI agents with SQL ability to any data source.\n\n🤩 [Learn more about Wren AI and our Mission](https://docs.getwren.ai/oss/overview/introduction/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme)\n\n## 🤖 A User-Centric, End-to-End Open-source SQL AI Agent - Text-to-SQL Total Solution\n\n### 1. Talk to Your Data in Any Language\n\n\u003e Wren AI speaks [your language](https://docs.getwren.ai/oss/guide/settings/pj_settings#change-project-language?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme), such as English, German, Spanish, French, Japanese, Korean, Portuguese, Chinese, and more. Unlock valuable insights by asking your business questions to Wren AI. It goes beyond surface-level data analysis to reveal meaningful information and simplifies obtaining answers from lead scoring templates to customer segmentation.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./misc/wren-lang.png\" style=\"max-width: 700px\"/\u003e\n\u003c/p\u003e\n\n### 2. Semantic Indexing with a Well-Crafted UI/UX\n\n\u003e Wren AI has implemented a [semantic engine architecture](https://www.getwren.ai/post/how-we-design-our-semantic-engine-for-llms-the-backbone-of-the-semantic-layer-for-llm-architecture/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme) to provide the LLM context of your business; you can easily establish a logical presentation layer on your data schema that helps LLM learn more about your business context.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./misc/wren-modeling.png\" style=\"max-width: 700px\"/\u003e\n\u003c/p\u003e\n\n### 3. Generate SQL Queries with Context\n\n\u003e With Wren AI, you can process metadata, schema, terminology, data relationships, and the logic behind calculations and aggregations with [“Modeling Definition Language”](https://docs.getwren.ai/oss/engine/concept/what_is_mdl/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme), reducing duplicate coding and simplifying data joins.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./misc/wren-context.png\" style=\"max-width: 700px\"/\u003e\n\u003c/p\u003e\n\n### 4. Get Insights without Writing Code\n\n\u003e When starting a new conversation in Wren AI, your question is used to find the most relevant tables. From these, LLM generates the most relevant question for the user. You can also ask follow-up questions to get deeper insights.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./misc/wren-insight.png\" style=\"max-width: 700px\"/\u003e\n\u003c/p\u003e\n\n### 5. Easily Export and Visualize Your Data\n\n\u003e Wren AI provides a seamless end-to-end workflow, enabling you to connect your data effortlessly with popular analysis tools such as [Excel](https://docs.getwren.ai/oss/guide/integrations/excel-add-in/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme) and [Google Sheets](https://docs.getwren.ai/oss/guide/integrations/google-add-on/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme). This way, your insights remain accessible, allowing for further analysis using the tools you know best.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./misc/wren-excel.png\" style=\"max-width: 700px\"/\u003e\n\u003c/p\u003e\n\n## 🤔 Why Wren AI?\n\nWe focus on providing an open, secure, and accurate SQL AI Agent for everyone.\n\n### 1. Turnkey Solution\n\n\u003e Wren AI makes it easy to onboard your data. Discover and analyze your data with our user interface. Effortlessly generate results without needing to code.\n\n### 2. Personalized answers without exposing data to LLM\n\n\u003e Your sensitive information remains protected, with no risk of being trained to public LLMs, giving you secure, personalized insights while maintaining full control of your data.\n\n### 3. Open-source End-to-end Solution\n\n\u003e Deploy Wren AI anywhere you like on your own data, LLM APIs, and environment, it's free.\n\n## 🤖 Wren AI Text-to-SQL Agentic Architecture\n\nWren AI consists of three core services:\n\n- ***[Wren UI](https://github.com/Canner/WrenAI/tree/main/wren-ui):*** An intuitive user interface for asking questions, defining data relationships, and integrating data sources.\n\n- ***[Wren AI Service](https://github.com/Canner/WrenAI/tree/main/wren-ai-service):*** Processes queries using a vector database for context retrieval, guiding LLMs to produce precise SQL outputs.\n\n- ***[Wren Engine](https://github.com/Canner/wren-engine):*** Serves as the semantic engine, mapping business terms to data sources, defining relationships, and incorporating predefined calculations and aggregations.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./misc/how_wrenai_works.png\" style=\"max-width: 1000px;\"\u003e\n\u003c/p\u003e\n\n## ❤️ Knowledge Sharing From Wren AI\n\nWant to get our latest sharing? [Follow our blog!](https://www.getwren.ai/blog/?utm_source=github\u0026utm_medium=content\u0026utm_campaign=readme)\n\n## 🚀 Getting Started\n\nUsing Wren AI is super simple, you can set it up within 3 minutes, and start to interact with your data!\n\n- Visit our [Installation Guide of Wren AI](http://docs.getwren.ai/oss/installation).\n- Visit the [Usage Guides](https://docs.getwren.ai/oss/guide/connect/overview) to learn more about how to use Wren AI.\n\n## 📚 Documentation\n\nVisit [Wren AI documentation](https://docs.getwren.ai/oss/overview/introduction) to view the full documentation.\n\n## 🛠️ Contribution\n\nWant to contribute to Wren AI? Check out our [Contribution Guidelines](https://github.com/Canner/WrenAI/blob/main/CONTRIBUTING.md).\n\n## ⭐️ Community\n\n- Welcome to our [Discord server](https://discord.gg/5DvshJqG8Z) to give us feedback!\n- If there are any issues, please visit [GitHub Issues](https://github.com/Canner/WrenAI/issues).\n- Explore our [public roadmap](https://github.com/orgs/Canner/projects/12/views/1) to stay updated on upcoming features and improvements!\n\nPlease note that our [Code of Conduct](./CODE_OF_CONDUCT.md) applies to all Wren AI community channels. Users are **highly encouraged** to read and adhere to them to avoid repercussions.\n\n## 🎉 Our Contributors\n\u003ca href=\"https://github.com/canner/wrenAI/graphs/contributors\"\u003e\n  \u003cimg src=\"https://contrib.rocks/image?repo=Canner/WrenAI\" /\u003e\n\u003c/a\u003e\n\n\u003cp align=\"right\"\u003e\n  \u003ca href=\"#top\"\u003e⬆️ Back to Top\u003c/a\u003e\n\u003c/p\u003e\n","funding_links":[],"categories":["[Wren](https://www.getwren.ai/)","TypeScript","Sql Generation","Table of Contents","Integrations","Tools \u0026 Frameworks","开源工具","A01_文本生成_文本对话","Large Language Models","ai","sql","Repos","Table of Open-Source AI Agents Projects","Corporate and Analytical Applications","\u003ca name=\"TypeScript\"\u003e\u003c/a\u003eTypeScript","🤖 Deep Research Systems"],"sub_categories":["Links","Agent","ETL and Data Processing","Text2SQL","SQL增强","大语言对话模型及数据","AI Development Platforms","RAG and Business Analytics","🌐 Open-Source Deep Research Implementations"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCanner%2FWrenAI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCanner%2FWrenAI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCanner%2FWrenAI/lists"}