One Engine • Four Surfaces • Smarter, Faster, Cheaper

Smarter, Faster, Cheaper Coding.

Albert automatically routes every programming task to the best-value model—delegating routine steps to fast, inexpensive specialists and escalating complex reasoning to frontier models.

albert --workspace ~/Projects/my-app

❯ albert: Refactor auth router to support scoped API tokens and update tests.


Conductor: GPT-5.5 Medium Task classified as Code Refactoring (Tier 2)

Delegated: Gemini 3.8 Flash High Applied patch to src/auth/token.ts [12 files checked, 44 tests pass]

Receipt: 1.2s • $0.0034 (Saved 84% vs fixed Frontier model)

One Unified Engine, Four Surfaces

Start a conversation on the web, continue it in VS Code, inspect it on Desktop, or trigger it from your terminal.

🖥️

Desktop App

Native macOS and Windows application with tabbed multi-session workflows.

Get Started
🧩

VS Code Extension

In-editor coding assistant with diff snapshots and direct canvas integration.

Get Started
🌐

Chrome / Web

Zero-install browser interface connected to your active local workspace server.

Open Web App
⚡

Terminal CLI

Fast, keyboard-first CLI that attaches directly to the shared Studio engine.

Copy Command

Why Developers Choose Albert

Built for production engineering without bloated token costs.

🎯

Automatic Model Routing

Albert evaluates the semantic difficulty of each turn, selecting the most cost-effective specialist model and escalating only when complex mathematical or architectural reasoning is required.

🛡️

Durable Permissions

Local-first workspace execution with granular, durable permissions. Approve tool actions once per workspace without annoying repeated prompts, all backed by strict project isolation.

📊

Transparent Accounting

Review model usage and your total Albert charges in the Albert Records panel. Albert applies a 20% markup to its recorded usage costs, and deducts the total from your prepaid balance.

Long conversations. Automatically managed context.

Albert separates saved conversation history from the smaller working context an AI model can use for each response.

Keep current work in focus

Albert's engine checks the selected model's context allowance and automatically prepares a smaller working view as the conversation grows. It carries forward recent messages, instruction excerpts and records of completed actions.

Retrieve earlier details

Older conversation records are archived outside the active model context. Albert can search and retrieve those records when needed, rather than sending the entire history with every response.

Prepare memory in the background

The engine builds an index of older messages asynchronously to help find relevant history. This background indexing is separate from AI summarization; it does not mean every memory operation happens without a pause.

Extended memory, not infinite tokens. Saved history can extend beyond one model's context window, but each response still has input and output limits. Retrieval may miss relevant details, and storage and processing limits still apply. Automatic context management is implemented; seamless long-conversation recovery is still being improved in this preview, and context-limit errors or interruptions can still occur. Albert does not promise unlimited storage, perfect recall or conversations that never need recovery.

Download Albert Studio

Desktop and VS Code release v0.1.20 (active preview). Download a prebuilt app below, or set up from source further down.

Mac (Apple Silicon)

Albert Studio Desktop for macOS on Apple Silicon (arm64). Includes the Albert CLI.

Download DMG

First launch: the app is not yet signed with an Apple Developer ID, so macOS Gatekeeper will warn that it cannot verify the developer. To open it anyway, right-click (or Control-click) the app and choose Open, or approve it under System Settings › Privacy & Security. Only do this for a DMG downloaded from the GitHub release link above.

Mac (Intel)

Albert Studio Desktop for Intel Macs (x64). Includes the Albert CLI.

Download DMG

This app is not yet signed with an Apple Developer ID. On first launch, right-click the app and choose Open, or approve it under System Settings › Privacy & Security. Verify the release checksum before installing.

VS Code Extension

Install the VSIX in VS Code via Extensions › … › Install from VSIX, or run code --install-extension albert-studio-0.1.20.vsix.

Download VSIX

Requires the Albert CLI. The extension does not include the engine. Install the Desktop app above (the CLI is bundled inside it and found automatically) or set up the CLI from source below.

Windows (x64)

Albert Studio Desktop for Windows x64. Includes the Albert CLI.

Download installer

The installer is unsigned, so Windows SmartScreen may show a warning. Download it only from the GitHub release link above and compare its SHA-256 checksum with the release manifest.

Windows (ARM)

Albert Studio Desktop for Windows ARM64. Includes the Albert CLI.

Download installer

The installer is unsigned, so Windows SmartScreen may show a warning. Verify the release checksum before installing.

Desktop downloads and the VS Code extension are hosted on the GitHub release page for v0.1.20. Source access is available to invited collaborators.