Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/bolt-builder/bolt-cli/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks you through installing Bolt, launching it in a project, connecting an AI provider, and running your first prompt. The whole flow takes under a minute.
1

Install Bolt

The quickest path is the official install script, which works on macOS and Linux:
curl -fsSL https://raw.githubusercontent.com/bolt-builder/bolt-cli/dev/install | bash
Prefer a package manager? Install globally with npm, bun, pnpm, or yarn:
npm i -g @bolt-builder/bolt-cli
See the Installation guide for all methods, including Homebrew, Chocolatey, Scoop, and Windows-specific notes.
2

Open your project

Navigate to any project directory and launch the interactive TUI:
cd my-project
bolt
Bolt picks up your project context automatically — reading your file tree, understanding the stack, and making it available to every agent from the moment you open it.
3

Configure an AI provider

On first launch, Bolt will prompt you to configure a provider if none is set. You can also run this at any time:
bolt providers
This opens the provider management flow where you can add API keys for OpenAI, Anthropic, and other supported LLM providers. Configuration is saved to .bolt/bolt.jsonc in your project root.
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    // Provider config goes here
  }
}
4

Type a prompt and explore agents

Once inside the TUI, type your prompt and press Enter. Use Tab to switch between Bolt’s ten built-in agents at any time — the current agent is shown in the status bar.You can also run prompts directly from the command line without opening the TUI:
# Non-interactive prompt using the default agent
bolt run "explain this codebase"

# Use a specific agent
bolt run --agent ask "what does this project do?"

# Attach the TUI to a running server (local or remote)
bolt attach <url>

​
Built-in agents

Switch agents with Tab in the TUI, or pass --agent <name> to bolt run. Each agent has a defined access level to match its purpose.
AgentAccessDescription
codeFullDefault: reads, writes, and runs code
planReadExplores the codebase and produces a plan without changing files
askReadQuestions and research — no file edits
code-reviewReadReviews changes for correctness, style, and security
debugFullDebugs failing tests, crashes, and logic errors
refactorFullSafe refactoring with test verification at each step
docsEditWrites and updates documentation and comments
securityReadSecurity audit: vulnerabilities, secrets, patterns
migrateFullFramework upgrades and dependency migrations
perfFullPerformance analysis and optimization
There are also two built-in subagents for delegation: @general for complex multi-step tasks and @explore for fast read-only codebase research. You can define your own agents as Markdown files or generate one with bolt agent create.

​
Common commands to try next

# Review staged changes with a pass/fail exit code
bolt review --staged

# Generate a commit message for staged changes
bolt commit

# List and manage sessions
bolt session list

# View token usage and cost statistics
bolt stats

# Query the local session database
bolt db
Pass --mini to bolt or bolt attach for a compact UI that takes up less terminal space — great for smaller windows or split-pane layouts.
bolt --mini
bolt attach --mini <url>
bolt run accepts --auto, --yolo, and --dangerously-skip-permissions flags that auto-approve all permission prompts without asking. Use these only in trusted environments — they allow the agent to read, write, and execute without confirmation.
bolt run --auto "refactor this module"
bolt run --yolo "refactor this module"
bolt run --dangerously-skip-permissions "refactor this module"
Bolt supports shell completions for bash, zsh, fish, and other shells. Generate and install completions with:
bolt completion
Follow the printed instructions to source the completion script in your shell config.

Build docs developers (and LLMs) love

Get started for freeTalk to us