opensource/WrenAI
3
0
Fork 0
mirror of https://github.com/Canner/WrenAI.git synced 2026-09-01 15:34:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

Introduce WrenAI overview and advantages (#2293)

Browse Source
This commit is contained in:
Howard Chi
2026-05-15 15:31:31 +08:00
committed by GitHub
parent 6ab5d7b44d
commit 7156bcbc73
1 changed files with 22 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+22 -22
View File
@@ -44,6 +44,28 @@
---
## 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. Self-hostable. Apache 2.0.
![Wren AI architecture](./misc/wren-ai-architecture.png)
<!--
🎨 OPTIONAL: replace the ASCII block above with a proper architecture diagram.
Suggested: 3-row stack with the same labels but in your brand palette.
Save under /assets/architecture.svg and use:
<img src="./assets/architecture.svg" alt="WrenAI architecture" width="720" />
-->
## Why agent builders pick WrenAI
- **Open by default** — 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** — 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** — 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. Not chat history.
- **Sits on top of your existing stack** — warehouse, transformation pipelines, your existing semantic layer. Not another tool to maintain.
## The problem
Your AI agent reads `customers_v3.status = 4` and confidently tells you "active users grew 12%" — but half those rows were service accounts. The schema doesn't know that. Neither does your agent.
@@ -102,28 +124,6 @@ Or just ask your agent in natural language — it uses the context layer to reso
**Want to try it without your own database?** Tell the agent to run `wren-onboarding` with the bundled `jaffle_shop` sample dataset — 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 — soon — 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.
![Wren AI architecture](./misc/wren-ai-architecture.png)
<!--
🎨 OPTIONAL: replace the ASCII block above with a proper architecture diagram.
Suggested: 3-row stack with the same labels but in your brand palette.
Save under /assets/architecture.svg and use:
<img src="./assets/architecture.svg" alt="WrenAI architecture" width="720" />
-->
## Why agent builders pick WrenAI
- **Open by default** — 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** — 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** — 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. Not chat history.
- **Sits on top of your existing stack** — warehouse, transformation pipelines, your existing semantic layer. Not another tool to maintain.
## Two beats: scaffold fast, enrich deep
```bash