Give AI agents the context to query business data correctly through the open context layer that gives AI agents grounded, governed memory, context, SQL across 20+ data sources, that helps you build agentic GenBI, text-to-sql, dashboards, and agentic analytics.
WrenAI is an open-source context layer, distributed as a Python package (`pip install wrenai`), that gives AI agents the business semantics, SQL generation capabilities, and governed memory needed to query structured data correctly across more than 20 sources including PostgreSQL, BigQuery, and DuckDB. Rather than forcing each agent to rediscover schema meaning independently, WrenAI provides a shared interface through a CLI and a small discovery stub installed via `npx skills add Canner/WrenAI`, which auto-detects Claude Code alongside Cursor, Cline, and other clients. Once the stub is in place, agents fetch workflow guides through `wren skills get` commands and generate validated SQL through `wren ask`, with dry-plan validation and structured error hints built in as correctness primitives. The project targets agent builders, data teams, and developers building text-to-SQL tools, agentic analytics, or business intelligence dashboards who need a version-controlled, Git-friendly context store that sits on top of existing warehouses and transformation pipelines rather than replacing them.
- ✓License: NOASSERTION
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/Canner/WrenAI && cp WrenAI/*.md ~/.claude/agents/7 items en este repositorio
Connect SaaS data (HubSpot, Stripe, Salesforce, GitHub, Slack, etc.) to Wren Engine for SQL analysis. Guides the user through the full flow: install dlt, pick a SaaS source, set up credentials, run the data pipeline into DuckDB, then auto-generate a Wren semantic project from the loaded data. Use this skill whenever the user mentions: connecting SaaS data, importing data from an API, dlt pipelines, loading HubSpot/Stripe/Salesforce/GitHub/Slack data, querying SaaS data with SQL, or setting up a new data source from a REST API. Also trigger when the user already has a dlt-produced DuckDB file and wants to create a Wren project from it.
Augment a Wren project with business context that DB schema cannot carry — enum value meanings, units (USD vs cents, ms vs sec), NULL semantics, magic sentinels (-1 = unknown), soft-delete default filters, business synonyms, time-grain / TZ conventions, cross-system identifiers, currency rules, canonical-table preferences, AND named aggregation metrics (ARR, churn, DAU, WAU, NRR) proposed as cubes. Runs in one of two modes selected at session start: `grill` (one question at a time, user-driven) or `auto-pilot` (agent infers and applies, escalates only on conflicts and high-blast-radius additions like new cubes / views / relationships). Reads everything under <project>/raw/ (PDFs, glossaries, handbooks, code, data dictionaries) and optionally samples low-cardinality columns from the live DB (grill mode), compares against the current MDL / cubes / instructions.md / queries.yml / memory pairs, then fills gaps via the ten-category gap catalog and the cube proposal flow. Confirmed findings are written back to the right sink. Use when: user says 'enrich context', 'augment my project', 'grill me on this project', 'auto-fill my context', 'agent doesn't understand our docs / enum values / units / null meanings', 'business context is missing', 'what does status=A mean', 'is this amount in USD or cents', 'we keep getting wrong aggregations', 'add cubes for ARR / DAU / churn', 'we have a handbook / glossary / data dictionary the agent should know'; or after generating an MDL and noticing the agent lacks business semantics.
Generate a Wren MDL project by exploring a database with available tools (SQLAlchemy, database drivers, MCP connectors, or raw SQL). Guides agents through schema discovery, type normalization, and MDL YAML generation using the wren CLI. Use when: user wants to create or set up a new MDL, onboard a new data source, or scaffold a project from an existing database.
Onboard a user to Wren Engine end-to-end. Walks through environment checks, project scaffolding, connection configuration via .env, and first query. Use when: user wants to install Wren Engine, set up a new data source connection, or bootstrap a new project from scratch. Triggers: '/wren-onboarding', 'install wren', 'set up wren engine', 'wren onboarding', 'connect new database to wren'.
Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics, revenue, customers, orders, trends, or any business data; user says 'how many', 'show me', 'what is the', 'top N', 'compare', 'trend', 'growth', 'breakdown'; user wants to explore, analyze, filter, aggregate, or summarize data from a database; agent needs to query data, connect a data source, handle errors, or manage MDL changes via the wren CLI.
Wren CLI for AI agents — a semantic SQL layer over 22+ databases (Postgres, MySQL, BigQuery, Snowflake, Spark, …). The actual workflow guides live inside the `wren` CLI itself; this is just a discovery stub. Use whenever the user asks a data question (how many, show me, top N, compare, trend, breakdown, metric, revenue, customers, orders), wants to install / set up Wren Engine, connect a new database, connect SaaS data via dlt (HubSpot, Stripe, Salesforce, GitHub, Slack), generate or regenerate an MDL project from a database schema, enrich a project with business context (enum meanings, units, cubes like ARR / DAU / churn), or turn a project's context layer into a shareable GenBI web app / dashboard and deploy it to Vercel or Cloudflare. Triggers: 'install wren', 'set up wren engine', 'connect database to wren', 'connect SaaS to wren', 'load hubspot / stripe / salesforce data', 'generate mdl', 'scaffold wren project', 'enrich wren context', 'augment my project', 'add cubes', 'build a dashboard', 'make a shareable analytics app', 'deploy my context layer as a web app', 'genbi app', 'wren onboarding', 'wren usage', 'wren generate mdl', 'wren dlt connector', 'wren enrich context', 'wren genbi'.
Turn a Wren project's context layer into a shareable, browser-side GenBI web app and deploy it to the user's Vercel or Cloudflare account. Orchestrates the full flow: `wren genbi build` returns a project-hydrated build instruction, the agent authors the app from scratch into apps/<name>/, then register → verify → deploy produce a shareable URL. Use this skill whenever the user wants to: build a dashboard from their Wren project, make a shareable analytics app, deploy their context layer as a web app, host a GenBI app on Vercel or Cloudflare Pages, or asks for a 'genbi app'.
Resumen de Subagents
<div align="center" id="top">
<a href="https://getwren.ai">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="./misc/wrenai_logo_white.png">
<img src="./misc/wrenai_logo.png" width="300px" alt="WrenAI">
</picture>
</a>
### The open context layer for AI agents over business data.
*Your agent doesn't know what your data means. We fix that.*
[Docs](https://docs.getwren.ai) · [Discord](https://discord.gg/5DvshJqG8Z) · [Vision](https://www.getwren.ai/post/the-missing-context-layer-for-ai-agents-over-business-data) · [Blog](https://www.getwren.ai/blog)
[](LICENSE)
[](https://pypi.org/project/wrenai/)
[](https://github.com/Canner/WrenAI/releases)
[](https://discord.gg/5DvshJqG8Z)
[](https://github.com/Canner/WrenAI/commits/main)
[](https://x.com/getwrenai)
[](https://cannerdata.com)
<a href="https://trendshift.io/repositories/9263" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9263" alt="Canner/WrenAI | Trendshift" width="250" height="55" /></a>
</div>
> 📣 **2026-05-07** — Wren Engine has merged into this repo under [`core/`](./core). The previous `Canner/wren-engine` repo is archived. The previous WrenAI GenBI app is preserved on the [`legacy/v1`](https://github.com/Canner/WrenAI/tree/legacy/v1) branch (tag `v1-final`). [Read the announcement →](https://github.com/Canner/WrenAI/discussions/2205)
<!--
📺 HERO DEMO (place here)
─────────────────────────
Suggested: a 5–10 second silent loop showing:
1. Terminal: `wren skills get onboarding` (agent fetches the workflow guide from the CLI)
2. Agent walks the user through setup, then writes SQL via `wren query` — visible reasoning trace
3. Final result table
Format: .gif (≤2 MB) or .mp4 (autoplay-muted).
Save under /assets/wrenai-demo.gif and use the line below:
<img src="./assets/wrenai-demo.gif" alt="Wren AI in action" width="820" />
-->
---
## What WrenAI is
WrenAI is the **open context layer** that gives your agents what schemas don't: business semantics, examples, memory, governance, and — soon — the unstructured corporate knowledge that lives in your docs, wikis, and chat threads. Built for the agent frameworks you already use.
## Why agent builders pick WrenAI
- **Open by default** — Open-sourced core, SDK, and skills through Apache-2.0 license.
- **Built for AI agents** — Skills, agentic architecture, context retrieval are first-class. Ships as SDKs for the agent frameworks that engineers already use.
- **Correctness as primitives** — rich schema retrieval, dry-plan validation, structured errors with hints, value profiling, eval runner. The agent orchestrates; the trace lives in the agent's reasoning.
- **Reviewable, reproducible context** — every definition, example, and mapping is versionable and evidence-linked. Git-friendly.
- **Sits on top of your existing stack** — warehouse, transformation pipelines, your existing semantic layer. Not another tool to maintain.
## With & Without Wren AI
Agents are everywhere. Claude Code, Cursor, ChatGPT, Aider, LangChain pipelines, Pydantic AI flows, in-house copilots, customer-facing apps. None of them should have to rediscover your business logic from scratch. With Wren AI, "the context layer," they query through a standalone, shared interface usable by every agent and person, not gated behind a single vendor's UI and architecture.
<img width="1445" height="758" alt="before & after" src="https://github.com/user-attachments/assets/d6ef8b73-b844-4e11-9586-b4f7ab6ae9dc" />
## 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.
### 1. Install the CLI
```bash
pip install wrenai # core (DuckDB included)
pip install "wrenai[postgres,memory]" # add per-datasource and memory extras as needed
```
> **Tip for users in mainland China:** If `pip install` is slow or fails, use the Tsinghua mirror:
> ```bash
> pip install wrenai -i https://pypi.tuna.tsinghua.edu.cn/simple
> ```
> If HuggingFace model downloads time out, add `export HF_ENDPOINT=https://hf-mirror.com` before running the CLI.
```
### 2. Install the discovery stub for your AI client
```bash
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` — everything else lives in the CLI.
### 3. Ask your agent to set things up
Open your agent in a project directory and say something like:
> "Use Wren to set up my Postgres database."
The agent runs `wren skills get onboarding`, follows the guide step-by-step,
checks your environment, creates a connection profile, scaffolds the project,
and runs a first query.
### 4. (Optional) Enrich the project
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.
### 5. Ask questions
> "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`.
**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.
## Two beats: scaffold fast, enrich deep
```bash
# Day 1 — agent-driven
wren skills get onboarding # workflow guide: set up project + first query
wren skills get enrich-context # workflow guide: add business context (cubes, units, enums)
# Day-to-day
wren query --sql '...' # query through the MDL semantic layer
wren ask "<question>" --guided # wrap a question for a weaker agent
wren ask "<question>" --direct # wrap a question for a stronger agent
```
Fast at first. Deep when you need it. Always reviewable and Git-friendly.
<!--
📷 OPTIONAL: 2-up screenshot showing grill mode (left) vs auto-pilot mode (right).
Save under /assets/two-beats.png
-->
## What's Included
- **Modeling Definition Language (MDL)** — models, columns, relationships, views, cubes, metrics, row-level / column-level access control (RLAC / CLAC)
- **Engine** — Apache DataFusion based, 22+ data sources
- **Memory & examples** — LanceDB-backed, hybrid retrieval, versionable
- **Agent SDK** — `wren-langchain` (LangChain / LangGraph), `wren-pydantic`; reference Python integration for other stacks
- **Governed execution primitives** — functions, dry-plan, row limits, access control
## What's next
- **Context enrichment skill** — `/wren-enrich-context` (grill + auto-pilot modes) hardened across MDL, instructions, queries, and memory
- **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](https://github.com/Canner/WrenAI/discussions) for what's prioritized next
- **Full governed execution** — audit logs, rate limits, approval workflow, data-flow inspector
<!-- TODO: vision_paper_en.md is currently at .tmp/roadmap-discuss/vision_paper_en.md — move to a published path (e.g. docs/vision-paper.md or repo root) and update this link before publishing. -->
Full roadmap and design notes: see the [vision paper](https://docs.getwren.ai/oss/introduction).
## Documentation
- [Quickstart](https://docs.getwren.ai/oss/get_started/quickstart) — from skill install to first answer
- [Concepts](https://docs.getwren.ai/oss/concepts/what_is_context) — what context is, what MDL is, how memory works
- [Connect a database](https://docs.getwren.ai/oss/guides/connect/overview) — Postgres, BigQuery, Snowflake, DuckDB, and more
- [Agent SDKs](https://docs.getwren.ai/oss/sdk/overview) — what's shipping today, what's next
## Community
- 💬 [Discord](https://discord.gg/5DvshJqG8Z) — chat with the team and other builders
- 🐙 [GitHub Discussions](https://github.com/Canner/WrenAI/discussions) — design conversations, RFCs, longer threads
- 🐦 [Twitter / X](https://x.com/getwrenai) — release notes and short updates
- 🗞 [Blog](https://www.getwren.ai/blog) — vision, post-mortems, deep dives
## Contributing
We build in the open. Issues, PRs, connector contributions, SDK integrations, docs fixes — all welcome.
- [Contributor guide](./CONTRIBUTING.md)
- [Connector ecosystem program](./docs/contributing-a-connector.md) — three-tier ownership: official, community-blessed, community-owned
- [Architecture map](./docs/architecture.md) — find the right place to land your change
- Looking for somewhere to start? Try the [`good first issue`](https://github.com/Canner/WrenAI/labels/good%20first%20issue) label.
<details>
<summary><strong>Project structure</strong> — click to expand</summary>
```
core/
wren-core/ Rust semantic engine (Apache DataFLo que la gente pregunta sobre WrenAI
¿Qué es Canner/WrenAI?
+
Canner/WrenAI es subagents para el ecosistema de Claude AI. Give AI agents the context to query business data correctly through the open context layer that gives AI agents grounded, governed memory, context, SQL across 20+ data sources, that helps you build agentic GenBI, text-to-sql, dashboards, and agentic analytics. Tiene 15.5k estrellas en GitHub y se actualizó por última vez today.
¿Cómo se instala WrenAI?
+
Puedes instalar WrenAI clonando el repositorio (https://github.com/Canner/WrenAI) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar Canner/WrenAI?
+
Nuestro agente de seguridad ha analizado Canner/WrenAI y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene Canner/WrenAI?
+
Canner/WrenAI es mantenido por Canner. La última actividad registrada en GitHub es de today, con 332 issues abiertos.
¿Hay alternativas a WrenAI?
+
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
Despliega WrenAI en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/canner-wrenai)<a href="https://claudewave.com/repo/canner-wrenai"><img src="https://claudewave.com/api/badge/canner-wrenai" alt="Featured on ClaudeWave: Canner/WrenAI" width="320" height="64" /></a>Más Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.