+### 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) ยท [Discord](https://discord.gg/wrenai) ยท [Vision](https://www.getwren.ai/post/the-missing-context-layer-for-ai-agents-over-business-data) ยท [Blog](https://www.getwren.ai/blog)
+
+[](LICENSE)
+[](https://pypi.org/project/wren-engine/)
+[](https://github.com/Canner/WrenAI/releases)
+
+[](https://discord.gg/wrenai)
+[](https://github.com/Canner/WrenAI/commits/main)
+[](https://x.com/getwrenai)
+[](https://cannerdata.com)
+
+
+
+
+
> ๐ฃ **2026-05-07** โ 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 โ](https://github.com/Canner/WrenAI/discussions/2205)
+
+
+
---
-## Why WrenAI?
+## The problem
-AI agents fail on business data not because they can't write SQL โ they fail because they don't know what your warehouse means. Overlapping tables, inconsistent naming, metric definitions scattered across dashboards and SQL files: an LLM with raw database access guesses just as badly as a new hire on day one.
+Your AI agent reads `customers_v3.status = 4` and confidently tells you "active users grew 12%" โ but half those rows were service accounts. The schema doesn't know that. Neither does your agent.
-WrenAI is the open context layer that fills that gap. You model your business in **[MDL](./core/wren-mdl/)** (Modeling Definition Language) โ entities, relationships, calculations, governed access patterns โ and any agent (Claude, Cursor, ChatGPT, internal copilots, customer-facing apps) queries through the same layer your analysts already use.
+Without business context, every AI agent over your data is one well-phrased question away from a confident, plausible, wrong answer.
-A Rust engine powered by [Apache DataFusion](https://datafusion.apache.org/) translates the modeled SQL and runs it against 20+ data sources (PostgreSQL, BigQuery, Snowflake, Spark, etc.). Use it as a Python SDK, a CLI, a WASM module in the browser, or as building blocks for agent skills.
+
-**Pre-aggregation cubes** โ model business metrics once (revenue, order count, retention) with measures, dimensions, and time grains. AI agents query cubes with a structured input instead of hand-writing `GROUP BY` / `DATE_TRUNC` SQL, cutting error rates substantially on small / local models. See the [Cube guide](./docs/core/guides/modeling/cube.md).
+## Quickstart
-## Quick start
+WrenAI is **agent-driven by design**: you install the skill bundle once, then let your AI coding agent (Claude Code, Openclaw, Hermes, Codex, etc.) drive the rest โ Python deps, DB connection, project scaffold, and first query.
-The fastest path is to let an AI coding agent (Claude Code, Cursor, Aider, etc.) drive the install:
+### 1. Install the skill bundle
```bash
-# Install WrenAI skills into your AI agent
npx skills add Canner/WrenAI --skill '*'
```
-Start a new agent session and ask:
+This installs the Wren skills into your agent's skill directory. Skills are workflow guides that teach AI coding agents how to drive the Wren CLI for you. See the [Skills reference](https://docs.getwren.ai/oss/reference/skills) for the full list.
-> Use the `wren-onboarding` skill to install and set up Wren AI Core.
+### 2. Ask your agent to set things up
-The `wren-onboarding` skill walks the agent through environment checks, package install, project scaffolding, the first data source connection, and a first query.
+Open your agent in a project directory and ask:
-Full CLI guide and manual install steps: [`core/wren/README.md`](./core/wren/README.md). Installable extras for each connector are listed there.
+```text
+Use the wren-onboarding skill to install and set up Wren AI.
+```
+The agent will check your environment, install `wren-engine`, create a connection profile, scaffold the project, and run a first query โ all in one flow.
+
+### 3. (Optional) Enrich the project
+
+Once onboarding finishes, give your project the business context schemas can't carry:
+
+```text
+Use the wren-enrich-context skill in grill mode.
+```
+
+Two modes: **grill** (one question at a time, you in the loop) or **auto-pilot** (agent reads `/raw/` and proposes). Both modes write to MDL, instructions, queries, and memory โ all reviewable, all Git-friendly.
+
+### 4. Ask questions
+
+```bash
+wren ask "who are our top 10 customers by sales this quarter?"
+```
+
+Or just ask your agent in natural language โ it uses the context layer to resolve schema, recall similar past queries, and write governed SQL.
+
+**Want to try it without your own database?** Tell the agent to run `wren-onboarding` with the bundled `jaffle_shop` sample dataset โ same flow, but you'll be querying a real warehouse end-to-end in a couple of minutes.
+
+## What WrenAI is
+
+WrenAI is the **open context layer** that gives your agents what schemas don't: business semantics, examples, memory, governance, and โ soon โ the unstructured corporate knowledge that lives in your docs, wikis, and chat threads. Built for the agent frameworks you already use. Self-hostable. Apache 2.0.
+
+
+
+
+
+## Why agent builders pick WrenAI
+
+- **Open by default** โ Apache-2.0 core, SDK, and skills. Your MDL belongs to you. Self-host is a first-class deployment, not a teaser.
+- **Built for AI agents** โ not retrofitted from BI. Skills, tool gating, task-scoped context retrieval are first-class. Ships as SDKs for the agent frameworks engineers already use.
+- **Correctness as primitives, not promises** โ 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** โ every definition, example, and mapping is versionable and evidence-linked. Git-friendly. Not chat history.
+- **Sits on top of your existing stack** โ warehouse, transformation pipelines, your existing semantic layer. Not another tool to maintain.
+
+## Two beats: scaffold fast, enrich deep
+
+```bash
+/wren-onboarding # Scaffold a Wren project from your DB (agent-driven)
+/wren-enrich-context # One skill, two modes: (Under development)
+ # grill โ one question at a time, you in the loop
+ # auto-pilot โ agent reads /raw/ and proposes
+wren ask "..." # Query through the context layer
+```
+
+Fast at first. Deep when you need it. Always reviewable. Always Git-friendly.
+
+
+
+## What works today
+
+- **MDL** โ models, columns, relationships, views, cubes, metrics, row-level / column-level access control (RLAC / CLAC)
+- **Engine** โ Apache DataFusion (Canner fork), 22+ data sources
+- **Memory & examples** โ LanceDB-backed, hybrid retrieval, versionable
+- **Agent SDK** โ `wren-langchain` (LangChain / LangGraph) shipping today; reference Python integration for other stacks
+- **Governed execution primitives** โ strict mode, denied functions, dry-plan, row limits, RLAC / CLAC
+
+## What's next
+
+- **Context enrichment skill** โ `wren-enrich-context` (grill + auto-pilot modes) hardened across MDL, instructions, queries, and memory
+- **End-to-end correctness primitives** โ value profiling, rich retrieval, structured errors, golden eval runner
+- **Agent-native distribution** โ first-class SDKs across major agent frameworks; see [GitHub Discussions](https://github.com/Canner/WrenAI/discussions) for what's prioritized next
+- **Full governed execution** โ audit logs, rate limits, approval workflow, data-flow inspector
+
+
+Full roadmap and design notes: see the [vision paper](./vision_paper_en.md).
## Documentation
-[Wren AI OSS Documentation](https://docs.getwren.ai/oss/introduction)
-
-
-## Supported Data Sources
-
-Wren Engine is built to work across modern data stacks, including warehouses, databases, and file-based sources.
-
-Current open source support includes connectors such as:
-
-- Amazon S3
-- Apache Spark
-- Apache Doris
-- Athena
-- BigQuery
-- ClickHouse
-- Databricks
-- DuckDB
-- Google Cloud Storage
-- Local files
-- MinIO
-- MySQL
-- Oracle
-- PostgreSQL
-- Redshift
-- SQL Server
-- Snowflake
-- Trino
-
-See the connector API docs in the project documentation for the latest connection schemas and capabilities.
-
-## Repository map
-
-| Path | What's there |
-|---|---|
-| [`core/`](./core) | Rust engine + Python/WASM bindings + CLI. The context layer's core machinery. |
-| [`core/wren-core/`](./core/wren-core) | Rust semantic engine (Cargo workspace). |
-| [`core/wren-core-base/`](./core/wren-core-base) | Manifest types (`Model`, `Column`, `Cube`, `Relationship`, `View`). |
-| [`core/wren-core-py/`](./core/wren-core-py) | PyO3 bindings (PyPI: `wren-core`). |
-| [`core/wren-core-wasm/`](./core/wren-core-wasm) | WebAssembly build for in-browser semantic SQL (npm: `wren-core-wasm`). |
-| [`core/wren/`](./core/wren) | Python SDK + `wren` CLI (PyPI: `wren-engine`). |
-| [`core/wren-mdl/`](./core/wren-mdl) | MDL JSON schema. |
-| [`skills/`](./skills) | CLI-based agent skills (`wren-generate-mdl`, `wren-usage`, `wren-dlt-connector`, `wren-onboarding`). |
-| [`sdk/`](./sdk) | Framework integrations. [`sdk/wren-langchain/`](./sdk/wren-langchain) (PyPI: `wren-langchain`) is shipped; CrewAI / Pydantic-AI / Goose / LlamaIndex / Mastra are _coming soon_. |
-| [`examples/`](./examples) | End-to-end example projects โ _coming soon_. |
-| [`docs/core/`](./docs/core) | Module documentation. |
+- [Quickstart](https://docs.getwren.ai/oss/get_started/quickstart) โ from skill install to first answer
+- [Concepts](https://docs.getwren.ai/oss/concepts/what_is_context) โ what context is, what MDL is, how memory works
+- [Connect a database](https://docs.getwren.ai/oss/guides/connect/overview) โ Postgres, BigQuery, Snowflake, DuckDB, and more
+- [Agent SDKs](https://docs.getwren.ai/oss/sdk/overview) โ what's shipping today, what's next
## Community
-- **Discord**: [discord.gg/canner](https://discord.gg/canner)
-- **Discussions**: [github.com/Canner/WrenAI/discussions](https://github.com/Canner/WrenAI/discussions)
-- **Issues**: [github.com/Canner/WrenAI/issues](https://github.com/Canner/WrenAI/issues)
+- ๐ฌ [Discord](https://discord.gg/wrenai) โ chat with the team and other builders
+- ๐ [GitHub Discussions](https://github.com/Canner/WrenAI/discussions) โ design conversations, RFCs, longer threads
+- ๐ฆ [Twitter / X](https://x.com/getwrenai) โ release notes and short updates
+- ๐ [Blog](https://www.getwren.ai/blog) โ vision, post-mortems, deep dives
+
+
+
+## Used by
+
+
+
+## Contributing
+
+We build in the open. Issues, PRs, connector contributions, SDK integrations, docs fixes โ all welcome.
+
+- [Contributor guide](./CONTRIBUTING.md)
+- [Connector ecosystem program](./docs/contributing-a-connector.md) โ three-tier ownership: official, community-blessed, community-owned
+- [Architecture map](./docs/architecture.md) โ 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.
+
+
+Project structure โ click to expand
+
+```
+core/
+ wren-core/ Rust semantic engine (Apache DataFusion)
+ wren-core-base/ Shared manifest types + MDL builder
+ wren-core-py/ Python bindings (PyPI: wren-core)
+ wren-core-wasm/ WebAssembly build (npm: wren-core-wasm)
+ wren/ Python SDK and CLI (PyPI: wren-engine)
+ wren-mdl/ MDL JSON schema
+sdk/
+ wren-langchain/ Reference agent SDK integration
+skills/ Agent skills for context authoring
+docs/ Module documentation
+examples/ Example projects
+```
+
+
+
+## Contributors
+
+
+
+
## License
-WrenAI is multi-licensed:
+Apache 2.0. See [LICENSE](./LICENSE).
-- **`core/**`, `sdk/**`, `skills/**`, `examples/**`, root-level files** โ [Apache License 2.0](LICENSE-APACHE-2.0)
-- **`docs/**`** โ [Creative Commons Attribution 4.0 International (CC BY 4.0)](LICENSE-CC-BY-4.0)
+---
-Future modules may be introduced under [GNU Affero General Public License v3.0](LICENSE-AGPL-3.0); the full text is committed here pre-emptively. See [LICENSE](LICENSE) for the authoritative path-to-license map.
+
-Published packages declare their effective license in their package manifest (`Cargo.toml`, `pyproject.toml`, `package.json`).
+*Come build the context layer with us.*
-## Our Contributors
-
-
-
+**If WrenAI helps you, drop a โญ โ it genuinely helps us hire and ship.**
-
- 
+ 
