Canner /WrenAI
GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.
★ 18,294⑂ 2,111👁 102⑃ 2,134● 612▤ 221
+72
日增长
+236
周增长
+413
月增长
18,294
stars
2,111
forks
102
watchers
2,134
prs
612
issues
221
releases
README
Open-source GenBI for AI agents Your agents generate governed SQL, deploy dashboards, and keep business definitions in Git, across 22+ data sources. Get started in 3 commands ↓ · Read the docs → · Join Discord → !Stars --- What WrenAI is WrenAI is the open-source generative BI (GenBI) engine. It gives the AI agents you already use (Claude Code, Cursor, MCP clients, LangChain) a governed semantic layer and an AI context layer, so they turn business questions into correct SQL, ship the answer as a shareable dashboard, and stay inside your guardrails. Schemas tell an agent where data lives. Wren tells it what the data means: approved metric definitions, enums, units, joins, worked examples, and the tribal knowledge buried in docs and chat threads. All of it lives as reviewable YAML and Markdown in a repo you own. Quickstart Three commands, then your agent does the rest. Works with Claude Code, Cursor, Cline, Codex, and 50+ other agents. 1. Install the CLI bash pip install wrenai Add connector extras as you need them, for example pip install "wrenai[postgres,memory]". 2. Teach your agent about Wren bash npx skills add Canner/WrenAI This installs a ~50-line discovery stub. Your agent fetches full workflow guides from the CLI on demand, so instructions always match the installed version. 3. Open your agent in a project folder and ask "Use Wren to set up my Postgres database." The agent checks your environment, creates a connection profile, scaffolds the project, and runs a first query. No database handy? Say "Use Wren with the bundled jaffle_shop sample" and run the same flow against a real sample warehouse. Slow pip install from mainland China? bash pip install wrenai -i https://pypi.tuna.tsinghua.edu.cn/simple If HuggingFace model downloads time out, run export HF_ENDPOINT=https://hf-mirror.com before using the CLI. Then keep going Once you're connected, these three prompts cover the whole GenBI loop: | Beat | Ask your agent | What happens | |---|---|---| | Know | "Enrich my Wren project with the business context in raw/." | Runs wren skills get enrich-context. Writes definitions, examples, and memory as reviewable files. | | Generate | "Who are our top 10 customers by sales this quarter?" | Recalls MDL context and past queries, writes governed SQL, executes via wren query. | | Deploy | "Turn that into a dashboard I can filter and share, deployed to Vercel." | Runs wren skills get genbi. Builds a browser-side app and returns a live URL on your Vercel or Cloudflare Pages account. | Follow the full quickstart → · Build & deploy a GenBI app → Why agent builders pick WrenAI - Answers and dashboards, not just SQL. Generate a governed answer, deploy it as a dashboard, share the URL. One agent-driven loop, end to end. - Correct instead of confidently wrong. Schema-aware retrieval, MDL planning, dry-plan validation, row limits, value profiling, and structured
Top issues
#1121Can't start wren-ai-service for a qdrant interaction error43 comments · 2025-01-15#1354无法启动成功,无法使用38 comments · 2025-03-04#1296Unable to run using Deepseek configuration,My version is 0.15.325 comments · 2025-02-13#710Support Oracle data source25 comments · 2024-10-03#768Try to run on kubernetes Bootstrap not working 18 comments · 2024-10-17#1368It is so difficult to setup the Ai Provider14 comments · 2025-03-05#1190An error occurred when using a custom model; please help me with this.14 comments · 2025-01-18#1393Unable to see container id for wren AI and in wren Ai having error "Failed to create asking task"11 comments · 2025-03-12
Discussions
#2788Add StarRocks as a first-class data source (correct SQL dialect)1 comments · 2026-10-05#2741multi data source1 comments · 2026-09-14#2538Enforcing MDL: rejecting SQL that violates declared relationships (working code)1 comments · 2026-07-18#2446windows launcher1 comments · 2026-07-07#2442WrenAI is featured in the ODAP Landscape 2026 — open scoring, challenges welcome0 comments · 2026-07-06#2205`Canner/wren-engine` is merging into `Canner/WrenAI` — both repos frozen now1 comments · 2026-04-30#2183WrenAI is featured on Shypd — 84K+ AI tools0 comments · 2026-04-02#2161Add Support for ScyllaDB (Cassandra-Compatible)0 comments · 2026-03-18
Latest release
wren: v0.18.0 wren-v0.18.0 2026-11-100.18.0 (2026-11-10) Features wren: serve a project-bound agent and governed MCP through a shared context layer (2848) (c4d6ac3) Bug Fixes wren: address deferred review findings from the serve-agent context layer (2852) (b7f972f) wren: keep result columns that share a name in JSON output (2822) (2f70e4a) wren: preserve physical-column renames across Ossie export/import (2837) (07e31d6) wren: respect CTE visibility when expanding semantic models (2833) (8edc086) wren: scope flag grouping to the select that groups it (2853) (affcac7)