Skip to content
Bandicot
  1. Home
  2. Use cases
  3. Terminal-first developers using CLI agents
Log inDocsStart free

For the terminal crowd

Your agent, with a memory of what it did.

Bandicot records every tool call, file change and token behind your agent sessions, and keeps approvals in a permissions file you can read.

Start freeRead the agent docs

Solo is free for one profile · providers bill you directly

Sign up·Log in·Pricing

available

Project

A durable boundary for files, context, and decisions.

in development

Model fit

A laptop-aware choice before a large local download.

in development

Team layer

People and agents sharing a project with explicit history.

The problem

A CLI agent is fast and forgetful. When the terminal closes, so does the record of what it ran and what it changed.

The promise

Sessions persist, effects are versioned, and the permissions file decides what runs without asking.

The picture

Keep your CLI habits and gain sessions, approvals and versions that outlive the terminal.

Why it holds
The host owns tool calls and records every effect; sessions reattach after a restart.
How soon
Point a project at your repo and run.
What it saves you
No lost scrollback, no rerunning a session to see what it changed.

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.

Agents with a project boundary

Available now

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.

Plans before tool work

Available now

Turn a vague request into an inspectable sequence of steps before tools begin changing the project.

The harness tracks dependencies and blocked steps. A conversation alone does not silently advance execution.

Recorded versions of the work

Available now

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.

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.

MCP connections with context

Available now

Connect MCP servers to a project when the work needs their tools or data.

MCP tools are called through the host, so approvals and versions cover them too.

Skills for repeatable work

Available now

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

Developers who run agents from a shell.

Not for you if

People who never open a terminal.

The offer

Shell Profile

Solo · free · 1 profile

  • Durable sessions that reattach
  • Approval rules in one permissions file
  • Run undo for a whole session
  • Tokens per turn

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

Start freeRead the agent docs

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

Is there a command-line client?+

Bandicot is a native Mac app with a terminal pane and agent tabs. The host does the work; the window shows it.

Where do the approval rules live?+

In one permissions file per setup. Anything it does not allow waits for you.

Can I use MCP servers?+

Yes. Install them per project. Their tools run through the host, so approvals and versions cover them.

Shell Profile

Sessions persist, effects are versioned, and the permissions file decides what runs without asking.

Start freeRead the agent docs

Solo is free for one profile · providers bill you directly

Sign up·Log in·Pricing

Your agent, with a memory of what it did.: Bandicot for Developers who live in the terminal.
Your agent, with a memory of what it did.. Every claim on this page names its status.
HomeSign upLog inPricingDocs

Explore another angle

One workspace, other ways in.

  • Keep the project. Change the model.: Bandicot for Cursor and IDE-agent users/l/cursorKeep the project. Change the model.People who use an AI editor and want the project to outlast the chat
  • Runbooks an agent can run, and you can audit.: Bandicot for Platform, SRE and DevOps teams/l/devopsRunbooks an agent can run, and you can audit.Platform and SRE teams with runbooks
  • 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