[verdict][curated prompt][source: boltai.com]

Can I vibecode BoltAI?

// buildable in a weekend, but real gaps stay open

A coding agent can one-shot a basic chat window that calls a few AI APIs. That reproduces only a small part of BoltAI. A credible replacement must remain fast with large histories and active streams, combine SwiftUI with purpose-built AppKit components where the framework falls short, and make focus, keyboard navigation, menus, windows, drag and drop, and global shortcuts behave like a real Mac app. It must also reproduce AI Workflows, Instant Chat, Instant Dictation, attachments, tools, provider-specific behavior, local persistence, sync recovery, and protected credentials. These are interacting product systems, not a collection of generated screens.

confidence: medium

what it is: Private native AI workspace for Mac with multiple models, agents, workflows, files, and tools

Buildability index · an editorial game

Price one-time weight: zero
Time multi-day weight: plus 1
Category ai assistants no weight
Moat execution quality · integrations · switching costs weight: minus 3
Confidence medium weight: zero
What you lose 5 items weight: minus 2
Site boltai.com (si apre in una nuova scheda) no weight

think twice

The moat outweighs the price: rebuilding this is a project, not an evening.

Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.

What you build

Build a performant native Mac chat client for a few AI providers with streaming, searchable history, attachments, agents, workflows, and basic MCP support.

what you need

macOS 13 or later
Xcode with a Swift 6 toolchain
API keys for the selected cloud providers
Ollama for optional local models
Accessibility and microphone permissions for system-wide workflows

Editorial comparison targets a personal local replacement, not feature parity with BoltAI's hosted, sync, mobile, or team services. Recheck price before merge.

The prompt

A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.

One-shot prompt EN

Build a personal local replacement for BoltAI in an empty repository.
Use Swift 6, SwiftUI, AppKit where necessary, Core Data, and macOS Keychain.
Do not offer alternative stacks or copy BoltAI branding or visual assets.
The goal is a performant native Mac AI workspace, not a web chat wrapped as a desktop app.
Make the first run work locally with one documented command.
Create a native sidebar for projects and chats, a conversation view, and a composer.
Keep navigation, typing, scrolling, and streaming responsive with large chat histories.
Profile those interactions and use AppKit-backed controls where naive SwiftUI falls short.
Support OpenAI, Anthropic, Google Gemini, and Ollama through documented APIs.
Store user-supplied API keys in Keychain.
Support streaming, cancellation, retry, regeneration, and recoverable partial responses.
Render Markdown, code, images, reasoning, citations, and tool results.
Add projects, reusable agents, saved prompts, chat forking, and full-text search.
Add reusable workflows that operate on selected text, clipboard content, and files.
Add a global Instant Chat panel that accepts files, models, agents, and tools.
Add Instant Dictation that transcribes speech and returns text to the original application.
Support basic local and remote MCP servers with per-agent tool selection.
Store chats and attachments locally with export and backup support.
Handle provider failures, rate limits, interrupted streams, and application relaunches safely.
Write focused tests for persistence, streaming state, workflows, and provider translation.
Create a README covering setup, permissions, performance testing, data, and limitations.
Do not add billing, licensing, telemetry, analytics, or proprietary BoltAI services.
Deliberately leave out BoltAI Cloud Sync, mobile apps, teams, and hosted AI service.
Deliberately leave out full import fidelity, production code execution, and long-tail providers.
Finish by running the focused tests and listing the exact commands used.

Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.

What you lose

AppKit-backed performance and responsiveness across large workspaces and conversation histories
carefully tuned keyboard navigation, focus, menus, panels, windows, drag and drop, and other native Mac behavior
AI Workflows that capture context from other applications and return formatted results where the user is working
Instant Chat and Instant Dictation as reliable system-wide workflows rather than ordinary in-app screens
maintained provider compatibility, Cloud Sync, mobile continuity, imports, backup recovery, and protected credential portability

Why people still pay

People do not pay for BoltAI because it is the only app capable of putting a prompt box beside an API. Many native and Electron clients already do that. They pay because BoltAI is a fast, coherent Mac workspace where long histories, streaming responses, keyboard navigation, global panels, dictation, workflows, files, and tools behave like one product. Achieving that requires continuous profiling, AppKit-level engineering, product taste, and repair of real-world edge cases. AI can generate a large SwiftUI codebase quickly; it cannot one-shot the accumulated judgment and maintenance required to make that code feel native and remain performant.

moat: Execution quality Integrations Switching costs what a moat is

Measured native performance, AppKit-level interaction engineering, product taste, workflow depth, provider compatibility, and durable workspace history.