One panel. Five tabs. Write a spec, drag a task to In Progress, and watch the AI implement it — locally or in the cloud, following Clean Architecture from the first file.
VS Code Marketplace release coming soon — install manually from GitHub Releases in the meantime.
SDD is the core idea behind Alpaquitay. Your spec.md is the single source of truth for requirements, progress, and AI context.
Write epics and tasks in plain Markdown. AI can generate the initial spec from your goal description.
The Kanban board derives its state from the checkboxes — no separate database, no sync problems.
Drag a task to In Progress. The AI plans files, generates code, and writes them to your workspace.
The task is auto-marked done in spec.md. Your git commit references #SPEC-002 for full traceability.
Drag a completed task back. Type what needs fixing. The AI re-implements with your feedback applied.
Non-technical stakeholders read spec.md and understand the full project state. No Jira login needed.
Everything in one panel — no context switching.
View and edit spec.md in the panel. Regenerate from AI. Convert existing YAML, OpenAPI, or Gherkin files into spec format.
Four columns: Backlog, Todo, In Progress, Done. State derived from spec.md — drag to implement, drag back to correct.
Conversational AI with streaming responses. Stack-aware system prompt. Task work streams progress here in real time.
Last 40 commits. Commits referencing #SPEC-XXX are linked to tasks. Full traceability from code to requirement.
Built-in: Refactor, Generate Tests, Create File, Generate from Spec, Project Builder, Daily Standup. Custom skills via UI or TypeScript.
Auto-extracts class names, exported functions, and completed features into .alpaquitay/memory.json. Keeps AI context coherent across sessions.
Scans package.json, requirements.txt, pom.xml, go.mod, .csproj. Generates architecture-specific prompts for 16+ stacks.
Generates Java, React, and Spring+React projects with strict Clean Architecture layers: domain → application → infrastructure. ISO 12207 compliant.
No Alpaquitay servers. Code and prompts go directly to your provider. API keys in OS keychain, never on disk.
Kanban card moves to Done in < 3 s after file generation. Format, validate, build, and test run asynchronously — results stream to chat. >95% faster than the blocking pipeline.
When you open the Architecture tab on a new or code-less project, Alpaquitay infers components from spec.md epics and workspace folders and generates the diagram automatically — no manual node placement.
How the extension is built — and how it builds your projects.
All processing happens inside the VS Code Extension Host (Node.js). The WebView SPA communicates via the VS Code postMessage API — no HTTP servers, no ports, no data leaving your machine unless you invoke a cloud AI provider.
Dependencies always flow inward. Infrastructure depends on Application; Application depends on Domain. The Domain layer has zero framework imports — it is pure business logic.
@RestController · JPA @Entity · @Configuration beans · Adapter classes that implement domain portsAlpaquitay scaffolds every new project with the correct package hierarchy from the first file. The AI is instructed to respect these boundaries in every subsequent code-generation step.
src/main/java/com/example/myapp/ │ ├── domain/ │ ├── model/ │ │ └── User.java # pure POJO │ └── port/ │ └── UserRepository.java # interface │ ├── application/ │ ├── service/ │ │ └── UserService.java │ └── dto/ │ ├── UserRequest.java │ └── UserResponse.java │ ├── infrastructure/ │ ├── persistence/ │ │ ├── UserEntity.java # @Entity │ │ └── UserJpaRepository.java │ ├── web/rest/ │ │ └── UserController.java# @RestController │ └── config/ │ └── BeanConfig.java │ └── shared/ └── exception/ └── GlobalExceptionHandler.java
src/ │ ├── domain/ │ └── model/ │ └── user.ts # TS interface │ ├── application/ │ ├── use-case/ │ │ └── getUser.ts │ └── store/ │ └── userStore.ts # Zustand/Pinia │ ├── infrastructure/ │ ├── api/ │ │ └── userApi.ts # fetch/axios │ └── storage/ │ └── localStorage.ts │ ├── presentation/ │ ├── components/ # reusable UI │ ├── pages/ # route-level views │ └── layout/ # shell / nav │ └── shared/ ├── hooks/ └── utils/
my-project/ │ ├── backend/ # Spring Boot (Maven) │ └── src/main/java/com/example/ │ ├── domain/ # model + port (no Spring deps) │ ├── application/ # service + dto │ ├── infrastructure/ # web/rest + persistence + config │ └── shared/ # exception + util │ ├── frontend/ # React + Vite (Clean Architecture) │ └── src/ │ ├── domain/ # TS interfaces (pure) │ ├── application/ # use-case + store │ ├── infrastructure/ # api + storage │ ├── presentation/ # components + pages + layout │ └── shared/ # hooks + utils │ ├── docker-compose.yml └── spec.md
When you drag a task card to "In Progress," this is the exact sequence of operations inside the extension.
The SPA fires task:start over postMessage with the task ID and full title from spec.md.
ProjectContextBuilder reads stack files (package.json, pom.xml, go.mod…) and builds the master prompt. HierarchicalMemory injects known classes, exports, and completed features from .alpaquitay/memory.json.
DeepAgentSkill sends the task + context to the AI and requests a JSON file plan: which paths to create or modify, in what order, with what Clean Architecture layer each file belongs to.
For each file in the plan, a second AI call generates the full content. SSE streaming sends tokens to the Chat tab in real time so you can watch the implementation happen.
MCPExecutor calls the filesystem MCP server to write each file at the planned path. Directories are created as needed, preserving the Clean Architecture layout.
The task checkbox is ticked in spec.md. A git commit is created via MCP with message feat: [task title] #SPEC-XXX for full traceability.
HierarchicalMemory scans the new files for class names, exported functions, and interfaces. These are appended to .alpaquitay/memory.json so the next task has full context.
Every provider is abstracted behind the same AIClient interface. The active provider, model, and token limit are resolved from AlpaquitayConfig — zero hardcoded values in the pipeline.
AIClient.streamChat(messages, { provider, model, maxTokens })AlpaquitayConfig.preferredProvider + ModelCatalogchat:token events → WebView renders livechat:done → task marked complete · spec.md updated · git commit createdStop building better prompts. Build autonomous agents that own entire workflows end-to-end. Every industry will have a winner — the moat is domain knowledge, not the LLM.
Based on TOGAF ADM, ArchiMate 3.2, and BIAN Service Domain patterns. Dependencies always point inward; adapters implement ports; the core never touches infrastructure.
domain/model.ts
domain/ → ports/ → application/ → infrastructure/. Dependency rule enforced at compile time.src/domains/{vertical}/
IDomainAgentShell.run()
.alpaquitay/{vertical}/. Any Alpaquitay AI provider as the generation backend.infrastructure/adapters/
shell.run('use-case-id', params)
The question is not which AI model you use. The question is: which repetitive process do you know better than anyone in your industry?
14 Live shells · 5 planned · All extending BaseDomainShell · 0 TypeScript errors
Every request flows through a unified pipeline: privacy protection → knowledge augmentation → multi-agent execution → recursive refinement → learning.
The reference implementation — every architectural layer demonstrated with production-ready TypeScript. CEFR A1→C2.
Choose your provider in Settings. The model list, context window, and max-tokens field update dynamically from the built-in ModelCatalog — no hardcoded values.
Runs any GGUF/GGML model on-device. Auto-detected at localhost:11434. No API key required. Small-model mode activates automatically for models under 4B params.
GUI model manager with OpenAI-compatible API. Auto-detected at localhost:1234. Supports any model loaded in LM Studio.
A living index of your project that grows as the AI works — stored locally in .alpaquitay/memory.json. Never sent to any server.
| Level | What is stored | Example key |
|---|---|---|
project | Name, description, architecture decisions | goal, stack |
component | Major subsystems | auth, dashboard |
module | Specific modules within a component | jwt-provider |
section | Logical sections within a module | token-refresh |
feature | Completed spec tasks + output files | SPEC-001 |
package | External packages and why chosen | jsonwebtoken |
class | Class names and their source files | UserService |
method | Exported functions and their files | calculateTotal |
annotation | Interfaces, types, enums | AuthPayload |
keyvalue | Ad-hoc key-value facts | db_url |
config | Configuration entries | max_upload_mb |
Install the extension, open your project folder, and press Ctrl+Shift+A to open the hub or Ctrl+Alt+A for the command menu.
Or search Alpaquitay AI in the Extensions panel inside VS Code.