Free Bandicot core
Available nowSolo is free with every capability for one profile. Bring a provider key, a local model, or both; a provider's own bill stays yours.
Paid plans add profiles to an account. Bandicot does not resell model tokens.
Agents that work while you do something else
Automations run inside a project on a schedule or on request. They use the same tools, approvals and versions as a chat, and the ledger shows what each run spent.
Solo is free for one profile · providers bill you directly
The problem
A script with an API key runs anything it is told, records nothing, and you find out what it did when something breaks.
The promise
An automation is an agent with a schedule and a gate. Every run is recorded, every write is approved or allowed by your rules.
The picture
The plan
Every card names its status. Available now means you can use it today; in development and direction mean it is not shipped yet.
Solo is free with every capability for one profile. Bring a provider key, a local model, or both; a provider's own bill stays yours.
Paid plans add profiles to an account. Bandicot does not resell model tokens.
Bandicot gives every agent a project, tools, a session that survives restarts, approvals, and a clear place to stop.
The native host owns execution facts. The model proposes work; it does not certify a write, spend, or success.
Keep files, context, plans, and decisions with the project instead of losing them in a disposable chat.
A session is anchored to a project boundary so a pivot starts from an intentional context, not accidental history.
Close a client or reconnect after a pause without turning the work into a brand-new conversation.
The host records session state and clients reattach to it. A browser view does not become the source of truth.
When work can change files or systems, Bandicot makes the decision visible before the effect lands.
The approval boundary fails closed when an action is not allowed. The model cannot grant itself permission.
Agents that run on a schedule or on request inside a project, under the same approvals as a chat.
Automations run on your Mac while Bandicot is open. There is no hosted runner.
Let an agent inspect, plan, and use tools inside the project you selected instead of an unbounded chat transcript.
The host controls tool calls, cancellation, permissions, and the final recorded result.
Keep a legible trail of the turn and its effects so a pivot can be reviewed instead of guessed at.
The host treats state changes as recorded events. Reverting is itself part of the history.
See the tokens, cache reads and cost of every turn, per session, profile and model, and the habits behind them.
Bandicot reports what the provider or local runtime exposes. A provider that hides usage shows a dash, never a guess.
Package a way of working once, and every agent in the project can use it.
Skills load on demand, so an unused skill costs no tokens in the prompt.
For you if
People with recurring work an agent could do.
Not for you if
One-off questions, and anything that must run while the Mac is off.
The offer
Team · $8.99 a month · up to 3 profiles
No contract. Cancel any time from your account and keep the plan until the end of the period you paid for.
Solo is free for one profile · providers bill you directly
Left off this page
Bandicot does these too, but they are not why this page exists. Anything marked in development or direction is not shipped yet.
Questions
No. They run on your Mac while Bandicot is open. There is no hosted runner.
Only what your permissions file allows. Anything else waits for approval, and every change is a version.
The one you pick for it: a hosted provider or a local model.
Background Crew
Solo is free for one profile · providers bill you directly
Explore another angle
Solo is free for one profile · providers bill you directly
Start free