Can I vibecode BoltAI?

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.