Try free
Open core strategy

Context you can read, run, and keep.

The context engine is open source. Your team and your AI agents query through it, and every commercial plan runs that same engine, in our cloud or yours.

Try Wren AI Cloud freeStar on GitHub17K+
  • Engine open source on GitHub
  • Your MDL lives in your git
  • Cloud, VPC, or air-gapped
Wren AI open coreLive
Canner/WrenAI
Public repository
17K+
Release activityShipping weekly
Weekly
Releases
Public
Roadmap
1,700+
On Discord

The engine that writes your SQL is public. Audit every line.

Illustrative. One engine powers open core and the commercial platform.

GitHub stars
17K+
Release cadence
Weekly
Discord members
1,700+
Community growth
5× YoY
Why it matters

Ecosystem-locked platforms ask for trust. Open core earns it.

Six questions a skeptic should ask. Flip the switch.

  • ✓ Open source
    Can you read the code?

    Open source on GitHub, end to end.

  • ✓ In your git
    Where do your definitions live?

    MDL files in your own git repo.

  • ✓ Portable
    What happens if you leave?

    Keep the engine and your models.

  • ✓ Anywhere
    Where can it run?

    Cloud, your VPC, or air-gapped.

  • ✓ Free
    How do you evaluate?

    Run it locally today, free.

  • ✓ Community
    Who improves it?

    Weekly releases, plus 1,700+ community members.

15Platforms
22Buyer factors

One scored comparison guide.

Open core vs. cloud-locked AI analytics, free to download and share with your team.

Get the comparison guideSee Wren AI vs. alternatives
The open core

LLMs don't know your data. The open core does.

The open-source engine sits between your agents and your data, applying shared definitions at query time. Every line is on GitHub.

View on GitHubRead the OSS docs
Data sources
20+

Queried in place

AI agents
60+

Over MCP

LLMs
Any

Bring your own

Definitions
MDL

Metrics as code, in git

Your agents
Claude
MCP
Cursor
MCP
Your agent
CLI
Context engineOpen source
MDLText-to-SQLMCPCLI
  1. 1Question arrives
  2. 2MDL context applied
  3. 3Governed SQL runs
Your data, in place
Snowflake
Warehouse
BigQuery
Warehouse
PostgreSQL
Database
Databricks
Lakehouse

Connect once. 20+ data sources, queried in place.

The boundary

What's open, what's commercial. Published, not fine print.

Everything commercial stacks on the open core. The layer you have to trust is the one you can read.

Commercial: everything in the open core, plus

  • The published boundary
View on GitHubCompare plans

The engine stays open because the engine is what earns your trust.

Three ways to run it

Start where your constraints are.

Same engine on every path. Your models move with you.

Same context engine

Open source

Wren AI OSS

For developers building their own agents.

  • Free and open source
  • Engine, MDL, MCP & CLI (no UI)
  • Community on Discord
View on GitHubRead the OSS docs
Recommended
Same context engine

Cloud

Wren AI Cloud

The GenBI agent for your team, plus MCP for your AI agents, managed by us.

  • Starts free, no infrastructure
  • GenBI Apps, agentic mode, dashboards
  • Scales with your team
Try Wren AI Cloud freeCompare plans
Same context engine

Self-hosted

Enterprise Plus

The full platform inside your network.

  • VPC, on-prem, or air-gapped
  • Access control, row & column security
  • Licensed by sessions, not seats
Request a demoSee on-premise architecture

FAQ

The questions skeptics should ask.

The context engine, the part that turns a question into governed SQL, is open source on GitHub for individual developers, used through the CLI. The commercial platform is built on that same engine and adds the advanced AI for specific scenarios (GenBI Apps, agentic mode, context preparation) plus the UI, access control, row- and column-level security, and support. One engine, two layers: open source built for individual developers, the commercial platform built for teams and enterprises.

Open source: the context engine for individual developers, used through the CLI and MCP server (no UI), with MDL modeling, a core text-to-SQL pipeline, and 20+ connectors. Commercial: the advanced AI harnesses (GenBI Apps, agentic mode, AI-assisted context preparation), the UI and dashboards, embedded APIs, access control with user and group management, row- and column-level security, advanced security, and support, delivered as Wren AI Cloud or self-hosted Enterprise Plus.

Your MDL files already live in your git repo, your data never left your warehouse, and the open-source engine keeps running without a license. You lose the commercial platform (GenBI Apps, agentic mode, the managed experience), not your context or your data.

Yes, that's the designed path. The engine and MDL are the same across OSS, Cloud, and Enterprise Plus, so the models you build on open source carry over. Many teams prove value on OSS or the free Cloud tier before rolling out company-wide.

Judge the cadence, not the promise: weekly public releases, a public roadmap, 17K+ GitHub stars, and 1,700+ Discord members growing 5× year over year. The engine is the foundation of every commercial plan, so keeping it healthy is the business.

Next step

Read the code. Star the repo.

Run the engine locally today. Talk to us when you want the platform on top.

Try Wren AI Cloud freeStar Wren AI on GitHubRequest a demo
Public repository
17K+
stars on github.com/Canner/WrenAI
$git clone https://github.com/Canner/WrenAI.git