Skip to content
Bandicot
  1. Home
  2. Use cases
  3. Model tinkerers who switch providers often
Log inDocsStart free

For people who try every model

Any model. One project. Honest numbers.

Bring hosted providers and local models into the same project. Bandicot keeps the context, records each model's tokens and cost, and shows the habits behind them.

  • Any model, one project
  • Local models in one click
  • See what every turn spent
Start freeSee local models

Solo is free for one profile · providers bill you directly

Sign up·Log in·Pricing

  1. 01

    Choose

    Pick local or remote for this task.

  2. 02

    Fit

    Check model and machine constraints.

  3. 03

    Install

    Laptop model path is in development.

  4. 04

    Work

    Use a project with sessions and approvals.

The problem

Every new model means a new app, a new chat and a cold start, and no way to compare how each one actually did on your work.

The promise

Switch the model, keep the project. The ledger shows what each one spent.

The picture

Any model, one project, and a clear view of how each one behaves on your work.

Why it holds
Provider adapters keep model choice apart from project state.
How soon
Add a key or install a local model, then pick it per session.
What it saves you
No new project setup for every new model release.

The plan

What does the work, and what is still being built.

Every card names its status. Available now means you can use it today; in development and direction mean it is not shipped yet.

Free Bandicot core

Available now

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.

A trusted harness around the model

Available now

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.

Projects that hold the work

Available now

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.

Durable work sessions

Available now

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.

A human gate for writes

Available now

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.

Choose the model that fits

Available now

Use a local endpoint, a private runtime, or a remote provider without rebuilding the project around one model lab.

Provider adapters keep model choice separate from project state. Remote providers receive the prompts sent to them.

One-click local installs

Available now

Pick a small local model from a pinned catalog and install it in one click, checksum verified.

Eight chat models from about 1.25 to 4 GB of memory, on Apple Silicon. Small models suit private, light work; they are not frontier models.

Hardware-aware model fit

Available now

Before a local model downloads, Bandicot checks it against your Mac's GPU memory budget and free disk.

The fit check reads the Metal working-set budget, not physical RAM, and counts weights, context cache and a stated reserve.

Every token in view

Available now

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.

For you if

People who try every new model.

Not for you if

People loyal to one vendor.

The offer

Model Habits

Solo · free · 1 profile

  • Hosted providers and local models side by side
  • One-click local installs
  • Tokens and cost per model
  • The Habits tab per model

Free for one profile, no card required. Add profiles when someone joins.

Start freeSee local models

Solo is free for one profile · providers bill you directly

Sign up·Log in·Pricing

Left off this page

Focus is a feature.

Bandicot does these too, but they are not why this page exists. Anything marked in development or direction is not shipped yet.

  • Teams across machines
  • Shared compute, intentionally routed
  • Optional access controls
  • Nested profiles

Questions

Questions before you start

Which providers are supported?+

The connect-a-model docs list them. Each provider bills you directly and receives the prompts sent to it.

Can I run models locally?+

Yes: 8 small chat models install in one click on Apple Silicon, each checked against your GPU memory first.

Is it free?+

Solo is free with every capability for one profile.

Model Habits

Switch the model, keep the project. The ledger shows what each one spent.

Start freeSee local models

Solo is free for one profile · providers bill you directly

Sign up·Log in·Pricing

Any model. One project. Honest numbers.: Bandicot for Model tinkerers and early adopters.
Any model. One project. Honest numbers.. Every claim on this page names its status.
HomeSign upLog inPricingDocs

Explore another angle

One workspace, other ways in.

  • Every model run, with a receipt.: Bandicot for ML and AI researchers/l/researchEvery model run, with a receipt.Researchers comparing models
  • See what every turn spent.: Bandicot for Developers and teams paying per token for agent work/l/costSee what every turn spent.Anyone whose agent bill keeps growing
  • Agent work, native on your Mac.: Bandicot for Mac-native users/l/macosAgent work, native on your Mac.Mac users who want a native app, not a browser tab

Solo is free for one profile · providers bill you directly

Start free

Ask it anything.
Then hand it the work.

Solo is free for one person. Every plan has every capability, and your model provider bills you directly.

Download for MacSee plans
how to stop an AI agent from running commands without asking
Bandicot · LearnAn approval gate stops an AI agent before an action with side effects, such as a shell command, a push or a write outside its rules, until a person says yes.Read the full answer →
  • TerminalAgent calls sit on a vertical icon rail8862102a
  • ChatOne auto viewe889d9cd
  • SetupDrop a setup file on the window, type keys at a hidden prompt, and a second user lands on the same setupb3315485
  • PermissionsAuto is the only permission mode, tuned by permissions.json; dock reads Work | Team | Versions and never clips545d855a
  • TeamYour agent reads team channels and drafts posts behind a broker2cffe87c
  • MacsA sleeping Mac's schedules run on your awake Mac that holds the project, handed back on wake3ee6c14d
  • MacsAnswer and start work across your own Macs9cbff698
  • SetupOne portable setup file9cac30cf
  • TeamOffline mailboxc3f84303
  • TeamYour own Macs as one group2d761c37
  • VersionsSync a folder with your team5e88fb2c
  • TeamAcross networkse8d84155
  • TerminalAgent calls sit on a vertical icon rail8862102a
  • ChatOne auto viewe889d9cd
  • SetupDrop a setup file on the window, type keys at a hidden prompt, and a second user lands on the same setupb3315485
  • PermissionsAuto is the only permission mode, tuned by permissions.json; dock reads Work | Team | Versions and never clips545d855a
  • TeamYour agent reads team channels and drafts posts behind a broker2cffe87c
  • MacsA sleeping Mac's schedules run on your awake Mac that holds the project, handed back on wake3ee6c14d
  • MacsAnswer and start work across your own Macs9cbff698
  • SetupOne portable setup file9cac30cf
  • TeamOffline mailboxc3f84303
  • TeamYour own Macs as one group2d761c37
  • VersionsSync a folder with your team5e88fb2c
  • TeamAcross networkse8d84155

Product

  • Work
  • Team
  • Versions
  • Automatons
  • Sub-agents
  • Skills, plugins and MCP

Safety

  • Approvals
  • Undo a run
  • Local models
  • Setup file
  • Security

Use cases

  • Teams
  • Agencies
  • Founders
  • Consultants
  • Token costs
  • Cursor users
  • ChatGPT users
  • All use cases →

Learn

  • Approval gate
  • Undo an agent run
  • Tokens per solved task
  • Frozen prompt prefix
  • Sub-agents
  • Automatons
  • Setup file
  • Every answer →

Resources

  • Get started
  • Changelog
  • Connect a model
  • FAQ
  • llms.txt
  • Knowledge gallery

Company

  • Pricing
  • Mission
  • Terms
  • Privacy
  • Cookies
bandicotbandicot
© 2026 BandicotLast change shipped Oct 18, 2026 · 8862102ahi@apparatdynamics.comllms.txtSitemap