// devtools · Canner/WrenAI

WrenAI

WrenAI est un projet de développement open source, créé par Canner (Canner/WrenAI sur GitHub). Il compte 17 823 étoiles sur GitHub et 2 040 forks, il est publié sous la licence NOASSERTION et a été mis à jour pour la dernière fois sur GitHub le 8 octobre 2026.

GenBI for AI agents - governed text-to-SQL and dashboards through an open context layer

★ 17,8 k étoiles⑂ 2,0 k forksNOASSERTIONmis à jour oct. 2026
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet

Détails du projet

Étoiles GitHub
17 823
Forks
2 040
Licence
NOASSERTION
Dernière mise à jour sur GitHub
8 octobre 2026
Catégorie
Développement
Type de fiche
Guide d'installation complet
Site officiel
Official site
// fonctionnement

Comment ça marche

  1. Model your context

    Decide which tables and business definitions belong in the semantic (MDL) layer.

  2. Get WrenAI

    Install the wrenai Python package, or add the agent skills with npx.

  3. Connect a data source

    Connect your warehouse or database and author the context with the included skills.

  4. Ask your first question

    Pose a natural-language question and inspect the governed SQL and chart it produces.

// fonctionnalités

Pourquoi on l'adore

Governed text-to-SQL

Questions are answered through a curated semantic layer, so generated SQL respects defined models and rules.

20+ data sources

Works across BigQuery, Snowflake, PostgreSQL, ClickHouse, Redshift, Databricks, DuckDB and more.

GenBI dashboards

Produces dashboards and charts, including browser-side apps powered by the WASM build of the engine.

Knowledge and memory

Keeps version-controlled instructions and saved queries, plus a local LanceDB memory index with hybrid retrieval.

Agent SDKs

Integrates with LangChain/LangGraph and Pydantic AI, with agent skills for context authoring.

Git-based workflow

Bind a directory once, then git push deploys to Wren Cloud - git is the interface.

Advertisement
// lancez-le

Lancez-le vous-même

  1. Clone the repository

    Get the source code from GitHub and enter the project directory.

    git clone https://github.com/Canner/WrenAI.git
    cd WrenAI
  2. Install the SDK

    The Python SDK and CLI install from PyPI.

    pip install wrenai
  3. Or add the agent skills

    Give your coding agent the WrenAI skills for context authoring.

    npx skills add Canner/WrenAI
// cas d'usage

Ce que vous pouvez créer

  • Let analysts ask a Snowflake warehouse questions in plain English with governed SQL
  • Give an AI agent safe, semantic-layer access to production data
  • Generate a KPI dashboard from a natural-language brief
  • Version-control your BI context (instructions and saved queries) like code
Advertisement
// faq

Questions fréquentes

Who maintains this project?

It is maintained by Canner (the Wren AI team) on GitHub.

Is it free to use?

The open-source core is free - the README's License section states Apache 2.0, while Wren Cloud and some enterprise features are commercial under the project's open-core model.

Does it need a paid API key?

You need credentials for your own data warehouse/database and an LLM for question answering; WrenAI itself does not sell query tokens.

How does it compare to alternatives?

Compared with raw LLM text-to-SQL, WrenAI's semantic layer and governed execution primitives (dry-plan validation, row limits, structured errors) are designed to make agent-generated SQL trustworthy.

How do I get started?

Run pip install wrenai, connect a database, author a small context, and ask your first question.

// continuez l'exploration

Outils similaires

Développement

context-mode

Context optimization for coding agents: sandbox tool output, keep sessions lean, remember more

★ 25,7 k étoilesElastic License 2.0
Voir le guide →
Développement

potpie

A context graph for the AI-native SDLC — so agents and humans share one map of the codebase.

★ 5,7 k étoilesApache-2.0
Voir le guide →
Développement

OpenContext

Personal context store for AI coding agents — your skills, always loaded.

★ 1,3 k étoilesMIT
Voir le guide →
Développement

ripwire

The ripgrep of AI context — a zero-dependency C++23 CLI + MCP server that maps your repo for coding agents

★ 2,4 k étoilesApache-2.0
Voir le guide →
Développement

repo2txt

Turn any GitHub repo into one formatted text file — perfect context for AI.

★ 1,8 k étoilesCustom
Voir le guide →
Développement

langextract

Google's Python library for extracting structured data from unstructured text with LLMs, with grounding

★ 38,9 k étoilesApache-2.0
Voir le guide →
// alternatives

Alternatives en Développement

Les autres projets de la catégorie Développement avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si WrenAI ne vous convient pas.

  • OpenCode★ 211,6 k

    The open source coding agent

  • Transformers★ 166,9 k

    The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.

  • claude-code★ 149,7 k

    Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase

  • cc-switch★ 141,3 k

    Cross-platform desktop all-in-one manager for Claude Code, Codex, OpenCode and other coding agents

  • codex★ 128,2 k

    OpenAI's lightweight coding agent that runs locally in your terminal

// plus en devtools

Plus en Développement

Projets de la catégorie Développement proches dans le catalogue, les plus proches en étoiles de WrenAI — continuez à explorer de part et d'autre.

  • gitdiagram★ 18,0 k

    Turn any GitHub repo into an interactive architecture diagram - just swap 'hub' for 'diagram'

  • rocketride-server★ 17,8 k

    A high-performance AI pipeline engine - build LLM workflows as portable .pipe files

  • TRL★ 19,7 k

    TRL — Hugging Face library for post-training foundation models: SFT, GRPO, DPO and more, Apache-2.0

  • cookbook★ 17,8 k

    Google's official Gemini API cookbook - examples, guides and end-to-end demos

  • jcode★ 20,4 k

    A high-performance coding agent harness in Rust - fast TUI, swarms and every provider

  • ag-ui★ 16,4 k

    Open, event-based protocol that connects AI agents to user-facing apps with streaming and shared state.

Obtenir WrenAI

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.