docs: rename wren-engine package references to wrenai (#2317)

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/core/guides/refine.md

@@ -18,14 +18,14 @@ Scaffolding gives you a baseline MDL. This recipe is how you close the loop —
 The memory layer is an optional extra. It is **not** included in the base CLI. Install it before running any `wren memory ...` command:
 
 ```bash
-pip install "wren-engine[memory]"
+pip install "wrenai[memory]"
 ```
 
 Combine with your data source extra as needed:
 
 ```bash
-pip install "wren-engine[memory,postgres]"
-pip install "wren-engine[memory,bigquery]"
+pip install "wrenai[memory,postgres]"
+pip install "wrenai[memory,bigquery]"
 ```
 
 Without the `memory` extra, the memory commands below will not be available.

docs/core/reference/architecture.md

@@ -113,7 +113,7 @@ See the [MDL schema reference](/oss/reference/mdl) for the full project structur
 
 ### Wren Python SDK
 
-The `wren-engine` Python package exposes the same plan-and-execute pipeline that the CLI drives. The CLI is a thin Typer wrapper over the SDK — both share the orchestration code, both can be embedded in agent frameworks, notebooks, and applications.
+The `wrenai` Python package exposes the same plan-and-execute pipeline that the CLI drives. The CLI is a thin Typer wrapper over the SDK — both share the orchestration code, both can be embedded in agent frameworks, notebooks, and applications.
 
 When invoked (via CLI or SDK), the orchestrator:
 

docs/core/sdk/langchain.md

@@ -36,7 +36,7 @@ pip install "wren-langchain[postgres,memory]"   # or mysql, bigquery, ...
 | `memory` | Enables the 3 memory tools (`wren_fetch_context`, `wren_recall_queries`, `wren_store_query`) |
 | `all` | All datasources at once — useful for experimentation, heavy for production |
 
-If `wren-engine` is already installed (e.g. you use the CLI), the bare `pip install wren-langchain` is enough — your existing extras carry over.
+If `wrenai` is already installed (e.g. you use the CLI), the bare `pip install wren-langchain` is enough — your existing extras carry over.
 
 ---
 
@@ -194,7 +194,7 @@ Cross-project joins must happen in Python, not in SQL — each project has its o
 
 ## Compatibility
 
-| `wren-langchain` | `wren-engine` | `langchain` | `langgraph` |
+| `wren-langchain` | `wrenai` | `langchain` | `langgraph` |
 |---|---|---|---|
 | 0.2.x | >= 0.5.0 | >= 1.0 | >= 1.0 |
 

docs/core/sdk/pydantic.md

@@ -38,7 +38,7 @@ pip install "wren-pydantic[postgres,memory]"   # or mysql, bigquery, ...
 | `memory` | Enables the 3 memory tools (`wren_fetch_context`, `wren_recall_queries`, `wren_store_query`) |
 | `all` | All datasources at once — useful for experimentation, heavy for production |
 
-If `wren-engine` is already installed (e.g. you use the CLI), the bare `pip install wren-pydantic` is enough — your existing extras carry over.
+If `wrenai` is already installed (e.g. you use the CLI), the bare `pip install wren-pydantic` is enough — your existing extras carry over.
 
 ---
 
@@ -215,7 +215,7 @@ Cross-project joins must happen in Python, not in SQL — each project has its o
 
 ## Compatibility
 
-| `wren-pydantic` | `wren-engine` | `pydantic-ai` |
+| `wren-pydantic` | `wrenai` | `pydantic-ai` |
 |---|---|---|
 | 0.1.x | >= 0.5.0 | >= 1.0, < 2.0 |
 

skills/AUTHORING.md

@@ -31,7 +31,7 @@ description: "What this skill does and when to trigger it. Include specific
   trigger keywords. This field is loaded at startup for every conversation."
 license: Apache-2.0
 metadata:
-  author: wren-engine
+  author: wrenai
   version: "1.0"
 ---
 ```

skills/index.json

@@ -1,5 +1,5 @@
 {
-  "name": "wren-engine",
+  "name": "wrenai",
   "description": "AI agent skills for Wren Engine CLI — semantic SQL layer for 22+ data sources.",
   "homepage": "https://wren.ai",
   "repository": "https://github.com/Canner/WrenAI",

skills/wren-dlt-connector/SKILL.md

@@ -3,7 +3,7 @@ name: wren-dlt-connector
 description: "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."
 license: Apache-2.0
 metadata:
-  author: wren-engine
+  author: wrenai
   version: "1.0"
 ---