start using MariaDB with your agents
sign up, open a project, and add MariaDB to its setup script in settings → server.
mariadb on a project is a running database server in each conversation's own sandbox, installed by the project's setup script and reachable by every agent in the project through the bash tool.
what agents do with it
the loop is migration, apply, inspect, repeat. an agent runs the app's migration command against the project's mariadb, checks the resulting schema with the mariadb client, seeds the fixtures the tests expect, and runs the suite. when something fails on a collation or a strict-mode setting, the agent reads the real error rather than guessing which of several plausible causes applied.
one project, one database engine
mariadb and mysql cannot coexist on a machine, and a setup script that tries both leaves a half-installed system behind. because projects are isolated and run in parallel, the usual answer is a second project rather than one crowded setup script, and each project keeps its own data directory either way.
example tasks
- 01
port the schema from the old dump and check every table came across.
the agent loads the dump into the project's mariadb, lists the tables and row counts from the client, and reports the ones that did not match.
bashreadgrep - 02
the nightly report query is wrong. work out where.
it seeds representative rows in the conversation's sandbox, runs the query in pieces against the live database, and shows which join drops the records.
bashedit
what to know before installing
the project needs a sandbox, and a database beside an application is the case for the standard size or larger. settings → server shows the setup script's last run with its exit code and output, so a failure is visible rather than silent.
how to install MariaDB
MariaDB goes in the project's setup script, not once per team and not on your laptop.
- give the project a sandbox
MariaDB runs in each conversation's sandbox, on your team's own sandbox provider account. an owner or admin connects a provider once on the team's providers page, then picks it and a default size for the project, at creation or later in settings → server. a project with no sandbox has nowhere to run it.
- add it to the setup script
settings → server holds the project's setup script, a bash script that runs once on each new sandbox, in /project, with sudo. add MariaDB's install commands there and save.
- the next sandbox runs it
the script runs when a conversation's sandbox is created or reused, on the conversation's first turn. settings shows the last run with its exit code and output, and a failed run leaves the sandbox usable rather than blocking the project.
- agents use it through bash
from then on every agent in the project reaches MariaDB with the bash tool, on the same filesystem as the checkout they are working in. the conversation's sandbox keeps it between turns, sleeping when idle and waking with the next one.
where MariaDB actually lives
each conversation in a project gets its own sandbox on your team's sandbox provider account, and the project's setup script in settings → server decides what is on it. two projects never share a filesystem, so a version pinned for one client cannot collide with another's.
the sandbox provider bills its machine time to your team's account while it runs, and aldena adds nothing. the sizes are on isolated projects, and what agents may run in the sandbox is governed by the project's tool permissions.
faq
can mariadb and mysql live in the same project?
no. the packages conflict, so a setup script should install one or the other, never both. since each project has its own setup script, running both usually means running two projects rather than one crowded machine.
what should the setup script do for mariadb?
add the mariadb apt repository, install mariadb server, enable the service, and check that it is active at the end. settings → server shows the tail of the last run's output, so a failed start reads as a real error rather than a bare exit code.
why would a project pick mariadb over mysql?
because the app already runs it. each conversation's sandbox is there to match one codebase's stack, so the honest answer is that the setup script follows your repository rather than a recommendation. switching means editing the script and starting a new conversation.
does anything persist between sessions?
only within a conversation. each conversation's sandbox keeps its files between turns, sleeping when idle and waking with the next one, so a seeded database is still there next time. a new conversation gets its own sandbox, and the setup script runs on it again. a conversation left quiet for 7 days gives its sandbox back, and its next turn starts fresh.
spin up your first project.
one project per client, product, or piece of work, staffed with intake, requirements, build and code review agents.
