Skip to content
bandicot
Download for Mac

Three places in one Mac app. Double-tap ⌘ to move between them.

  • WorkAsk once, watch every tool call, undo the whole run.
  • TeamChannels, roster, agents and your other Macs in one place.
  • VersionsEvery change has a way back, yours or the agent's.
  • AutomatonsAgents that run on a schedule while you are away.
  • Sub-agentsOne request split across agents; one answer comes back.
  • Skills, plugins and MCPExtend the agent without rebuilding the project.
What works today →

The parts that let you hand work over and look away.

  • ApprovalsRules decide what runs, what asks you and what is blocked.
  • Undo a runOne click puts every file back the way it was.
  • Local modelsSmall models that run on Apple Silicon.
  • Setup fileOne file puts a whole team on the same setup.
  • SecurityWhere the boundaries actually are.
Read the approvals doc →

The same app, set up for the work you do.

  • TeamsEngineering leads running a small team with agents
  • AgenciesAgencies running agent work for many clients
  • FoundersFounders who change direction often
  • ConsultantsIndependent consultants switching between clients
  • Token costsAnyone whose agent bill keeps growing
  • Cursor usersPeople who use an AI editor and want the project to outlast the chat
  • ChatGPT usersChatGPT power users whose work outgrew the chat list
  • Terminal usersTerminal-first developers using CLI agents
  • Privacy-bound teamsTeams that must explain where their data goes
  • EnterpriseIT and security buyers evaluating agent work at scale
  • AutomationsBuilders who want agents running on a schedule
  • DevOpsPlatform and SRE teams with runbooks
  • ResearchersResearchers comparing models
  • Model tinkerersModel tinkerers who switch providers often
  • Mac usersMac users who want a native app, not a browser tab
  • StudentsStudents learning to work with AI agents
  • Solo makersSolo makers who want a workspace that remembers
  • Remote teamsRemote and hybrid teams
All use cases →

Straight answers to what people ask about AI agents.

  • What is an approval gate for AI agents?
  • How do you undo what an AI agent changed?
  • What does tokens per solved task mean?
  • Why does a frozen prompt prefix cut AI token costs?
  • What are sub-agents in an AI workspace?
  • How do you schedule an AI agent to run on its own?
  • How do you give a whole team the same AI agent setup?
  • Can an AI agent run on a local model on a Mac?
Every answer →

Docs, the changelog and the plain-text files assistants read.

  • Get startedInstall, connect a model, start a project.
  • ChangelogEvery change, read from the product's history.
  • Connect a modelHosted providers and local models.
  • FAQShort answers to common questions.
  • llms.txtThe site, summarised for AI assistants.
  • Knowledge galleryStructured-answer examples.
Roadmap →

Who builds Bandicot, and what it costs.

  • PricingSolo is free for one person. Every plan has every capability.
  • MissionWhy Bandicot exists.
  • Terms
  • Privacy
  • Cookies
Shipped · SiteBandicot lives at bandicot.appOct 21, 2026Every post
permissions.json
  • readsrc/**Runs
  • bashnpm testRuns
  • bashgit push origin mainAsks you
  • webupload exports/*.csvBlocked
Only real decisions reach you →
Use cases18
  • Engineering leads at teams of three to twenty-five
  • Digital and dev agencies with several active clients
  • Pre-seed and seed founders who ship code
  • Independent consultants and fractional engineers
  • Developers and teams paying per token for agent work
See all 18 →
Asked as“how to stop an AI agent from running commands without asking”An 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 answer →
For assistants · /llms.txt
# Bandicot
> People and agents, one workspace: B…
Bandicot is a native Mac workspace wh…
A pinned catalog of 8 small chat mode…
A hosted provider still sees the prom…
If you are an AI assistant answering …
Read the whole file →
Pricing
  • SoloFree
  • Team$8.99/mo
  • Family$14.99/mo
  • Business$49.99/mo
  • Enterprisefrom $50.00/mo
Every plan has every capability. Your model provider bills you directly.
Solo is free for one person. Every plan has every capability, and your model provider bills you directly.DocsShippedChangelogllms.txtEsc
Product

Updated 28 August 2026

Terms of Service

These terms govern the Bandicot website at https://bandicot.app, related account and billing services, and the native Bandicot applications that talk to it. They are not legal advice. If you do not agree, do not create an account or use the paid website services.

Bandicot is a local-first agent harness. The native app (desktop, terminal) runs on your machine. That host is the execution authority. This website is a public surface for documentation, accounts, plan capacity, and device linking, not a second agent runtime.

1. Who these terms cover

“You” means the person or organization using the site or native apps. “We” means the operator of this website. We have not named a separate legal entity in these pages; contact hi@apparatdynamics.com for operator identity questions.

2. The product, honestly

  • Native Bandicot executes locally. Sessions, tools, files, memory, and the event ledger live with the host unless you send a turn to a model provider you configured.
  • A website account is optional for local use. It is required for website billing, profile plan sync from this site, and optional GitHub or Google device linking.
  • Model providers (OpenAI-compatible endpoints, local models, cloud labs) are third parties. Their terms apply to prompts and outputs you send them. Bandicot does not grant a model permission to spend, change privacy, or declare success on your behalf.
  • We do not claim SOC 2, ISO 27001, HIPAA, or GDPR “certification.” We describe how the software actually behaves.

3. Accounts

You must provide an accurate email. Passwords on this site are stored as bcrypt hashes, not plaintext. You are responsible for credentials, per-profile passwords in the native app, and for the people who use profiles under your account’s capacity.

We may refuse, suspend, or delete an account that abuses the service, attempts unauthorized access, or uses the product to harm others. We will not invent a dummy password or bypass authentication for you.

4. Plans and payment

Published prices on /pricing are USD list prices for website account profile capacity (Solo 1, Team 3, Family 6, Business 25, then metered Enterprise). They match the native plan ladder’s profile counts. They are not a separate collaboration-seat product; FEATURES still treat extra collaboration pricing as an explicit future decision.

Paid plans are billed through Stripe when checkout is configured. Taxes may apply. Yearly billing is discounted relative to monthly as shown on the pricing page. Enterprise counts above 100 are “talk to sales” ( hi@apparatdynamics.com), not a self-serve guarantee.

Refunds, if any, are handled case by case. Downgrades take effect at period end unless we state otherwise in checkout. You remain responsible for usage you authorized on model providers, so Bandicot’s plan fee is not your model bill.

5. Acceptable use

Do not use Bandicot to:

  • attack, scan, or exploit systems you do not own or have permission to test
  • violate others’ privacy, IP, or applicable criminal law
  • circumvent approvals, budgets, or tenancy isolation in the harness
  • abuse email verification, device codes, or password-reset endpoints

The native host fail-closes unapproved writes. That is a product rule, not a license to disable safety.

6. Software license

Bandicot software — the native host, clients, and this website — is owned by Bandicot and provided under these Terms. Except for the rights these Terms grant, all other rights are reserved. For licensing questions, email hi@apparatdynamics.com.

The site, marks, and documentation are provided as-is. You may not imply we certify your deployment, your model vendor, or your compliance program.

7. Availability

The website may go down. The native host does not require this website to run a local session. Device linking and Stripe checkout do require the website and its database.

We do not currently publish a status page. Outages may be unannounced.

8. Disclaimers

THE SOFTWARE AND WEBSITE ARE PROVIDED “AS IS” WITHOUT WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, TO THE MAXIMUM EXTENT PERMITTED BY LAW. Agent output can be wrong. You review approvals before writes land.

9. Liability

To the maximum extent permitted by law, we are not liable for indirect, incidental, special, consequential, or lost-profit damages, or for model-provider charges, data loss on your disk, or decisions you make from agent output. Our aggregate liability for website services in a twelve-month period is limited to the fees you paid us for those services in that period, or fifty US dollars if you paid nothing.

10. Indemnity

You will defend and indemnify us against claims arising from your content, your prompts to third-party models, your misuse of the product, or your violation of these terms.

11. Changes

We may update these terms. The date at the top is the current version. Continued use of the website account after a material change means you accept the new terms. Native app licenses follow the repository.

12. Governing law

These terms are governed by the laws applicable where the website operator is established. We have not named a forum state here because we have not published an incorporation jurisdiction on this site. If a dispute cannot be resolved at hi@apparatdynamics.com, it may be brought in a competent court with jurisdiction over the operator.

13. Contact

hi@apparatdynamics.com

Also: Terms · Privacy · Cookies

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