kyle-visner/stellarjay

**Stellar Jay is the open-source data store that powers
AvianSuite.** AvianSuite is an agent-native business
data platform: AI agents run business processes like sales follow-up and
bookkeeping on your company's data, and every change they make is versioned,
attributed to the agent that made it, and reversible. Think of it as Git for
your business data.
Agents connect over MCP. The server is listed in the MCP registry as
com.aviansuite/stellar-jay, and the CRM (Martin)
and bookkeeping (Magpie) apps run on
the same store. This project was formerly called JayBase.
- **Hosted:** AvianSuite runs Stellar Jay for you.
$20/month per store, with a 14-day free trial.
- **Self-hosted:** free and open source under the AGPL. The quick start below
gets a store running on your machine in a few minutes.
Agent setup
Connect an agent with the MCP server. On AvianSuite, add the remote server:
In Claude and ChatGPT, add a custom connector with the same URL.
For a self-hosted store, run the local server instead:
Install it with go install github.com/kyle-visner/stellarjay/cmd/stellarjay-mcp@latest.
Tools and details: docs/mcp.md.
Why
Clients want agents that do the work, not just read about it. But when an agent
writes straight into a CRM or ticketing system, one bad decision or runaway
loop can overwrite or delete records, and there is often no way back.
Stellar Jay is built so that can't happen:
- **Nothing is overwritten or deleted.** A correction or retraction is a new
entry, and the original stays in history.
- **Every change has a name on it.** Each agent gets its own token, so you can
see exactly which agent changed what, and when.
- **Any change can be undone.** Roll back everything one agent did in a time
window, with a preview first.
- **History is tamper-evident.** If anyone rewrites or removes past entries, it
shows.
- **Retries are safe.** An agent that retries after a timeout doesn't create
duplicates, and a write based on stale information is refused.
- **Your data stays flexible.** Facts are JSON, so new fields and new kinds of
records need no migrations.
Every fact keeps its evidence and the agent that recorded it, so any wrong one
is visible, attributed and correctable.
Who it's for
Developers, consultants, and small teams moving from read-only copilots to
agents that are allowed to act: operations, accounting, approvals, support, and
other work where the data matters. Each store serves one organization. Many
agents and apps can share it.
Quick start (self-hosted)
Requires Go 1.22 or later.
**1. Install and create secrets.**
init creates a data encryption key and prints an admin, writer, and reader
token once. Save them in a password manager.
**2. Start the server.**
It listens on 127.0.0.1:8080.
**3. Record a fact.** In another terminal:
expected_root is empty only for the first entry in a new store. After that,
read the current value from GET /v1/root and send it with each write, so a