Bkper CLI Agent

Use Bkper's dedicated terminal workspace for local files, commands, scripts, tests, and context-rich workflows.

Bkper CLI Agent is the interactive agent included with Bkper CLI. It runs in your terminal through a TUI and is not required when you connect Bkper to ChatGPT or Claude.

If you already like ChatGPT Work or Claude on desktop, start with Use Bkper with ChatGPT or Claude. Those assistants use their own models while the Bkper CLI and skill provide Book access and Bkper context.

Choose the Bkper CLI Agent instead when you want one focused terminal environment built specifically for local Bkper work. It uses selected Bkper AI models by default, with no separate model-provider account or API key, and can also connect to external providers.

Use it when

You prefer a dedicated Bkper workspace instead of adding Bkper to another assistant.
You want Bkper context and selected AI models ready after signing in.
You want an agent to inspect local project files or AGENTS.md.
You need shell commands, pipes, scripts, tests, or exported CSVs.
You are building a repeatable report, import, cleanup, or integration.
You want deterministic checks instead of raw AI answers for financial outputs.

For installation, authentication, and the command reference, see Bkper CLI. For browser-based assistant access, connect Bkper to ChatGPT or Claude.

Quick start

Authenticate with Bkper
```
bkper auth login
```
This authenticates the CLI Agent with the preconfigured Bkper AI provider. You can instead start the agent first and use /login; both flows share the same local credentials and identify the authenticated account by email. See Bkper AI Provider for the client-agnostic inference interface and Models and Usage for the current portfolio, model capabilities, rates, and allowance policy.
Start Bkper CLI Agent
```
bkper
```
or:
```
bkper agent
```
Optionally connect another model provider

Type /connect to choose an external subscription or API-key provider. Use /connect <provider> to target one directly, such as /connect openai or /connect anthropic.

Bkper CLI Agent terminal interface showing the Bkper ASCII art header, command shortcuts, context, and an active input prompt

Why use the dedicated workspace

Bkper CLI Agent is built on Pi Agent, an extensible agent harness with a terminal UI. The harness coordinates model sessions, context, tools, and iterative work. Bkper adds Book access, domain context, safety rules, and model configuration.

Use it when you want one focused environment for long-running local work instead of adding Bkper to another assistant.

We chose Pi because it is:

Token efficient — lean context and tool loading for longer, cheaper sessions.
Well implemented — a small, reliable core instead of a heavy black box.
Open source — inspectable, extensible, and easier to improve.
Provider agnostic — 15+ model providers, local models, and no vendor bias.
Bundled with Bkper — one install gives you the agent plus Bkper domain context.

Model providers

Bkper AI is already configured, so no separate model-provider setup is required. The CLI loads the current catalog and default from GET /v1/models; an explicitly saved model remains selected while it is available. See Models and Usage for the current portfolio, capabilities, rates, and allowance rules.

To use an external subscription or API key instead, type /connect and choose a provider. External costs, limits, and privacy terms are governed by that provider.

/login and /logout manage Bkper authentication.
/connect [provider] and /disconnect [provider] manage external model providers.

Built-in safety

The Bkper CLI Agent is configured to work in reviewable steps: inspect context, explain plans, show commands for Bkper writes, and wait for confirmation before mutating data. You still approve changes and review financial outputs.

Starter prompts

Explain the account types in this Bkper book and list anything that looks unusual.

Find possible duplicate transactions from last month. Do not modify anything; show me the query and reasoning first.

Write a script that exports a monthly profit and loss report from Bkper balances. Keep the calculation deterministic and add a simple test fixture.

Review unchecked transactions from this month and suggest what needs attention. Do not post, check, or edit transactions.

Prepare an exploratory tax worksheet for 2025 from my Bkper data. Use Bkper as the source of truth and mark assumptions explicitly.