Open source · MIT · self-hosted

Git for MongoDB,
built for AI agents

Give every AI agent its own branch of your database. Review what it wrote, merge what works — discard or undo the rest. Nothing touches production.

$ brew install argon-lab/tap/argonctl

the whole idea, in one loop

prodagentHEADbranch

$ argon sandbox create -p prod --ttl 1h

the agent gets its own branch — a real MongoDB database, prod untouched

p1 · price: 49p2 · price: 89p3 · price: 74branch: isolated

step through the full demo →

v2.0 shipped: engine, benchmarks, branch databases, data PRs, agent surfacenext · GCS chunk store, synchronous proxy capturechangelog →
18Ar

01Inert by design

Named after the noble gas for a reason

Argon — element 18 — is inert: it doesn't react with anything. That's the contract: experiments happen on branches, history is append-only, production is never touched.

0.86 ms

to create a branch — p50, measured on a 50k-entry project

479 B

of storage per branch — branches are metadata, not copies

diff → merge

adopt an agent’s work as a reviewed data PR — or undo it, per-actor

numbers from the public benchmark suite — reproduce them with docker compose up

02Familiar workflow

The Git muscle memory you already have

git (code)argon (data)
git initargon projects create
git branch feature-xargon branches create feature-x
git checkout feature-xargon checkout -b feature-x
git logargon time-travel info
git diff mainargon diff
git merge + PR reviewargon merge preview/apply
git reset --hardargon restore reset
git revertargon undo --actor agent:x

agents can drive all of this themselves via MCP: claude mcp add argon -- argon mcpsee the agent workflow

03How it works

One idea, carried all the way through

your app · your agents

any driver, unchanged

every write →

append-only log

pre/post images · actor · LSN

views →

branches

real MongoDB databases

time travel

any state, by LSN or time

undo

per-actor, conflict-safe

04Built in the open

Claims you can check

Deterministic replay, property-tested in CI — same history, same state, byte for byte

tests

Every number on this site reproduces with docker compose up

benchmarks

MIT licensed, self-hosted — your MongoDB, your data, your infrastructure

license

Postgres has Neon. MySQL has PlanetScale. SQL has Dolt. Data lakes have lakeFS. MongoDB has Argon.

Branch your MongoDB today

Open source, MIT licensed, self-hosted. Star the repo to follow along — or run the benchmarks yourself first.