AI Code Assistance — General Coding + Data + Data Science + AI Engineering

A Vibe Coding assistant for VS Code that goes far beyond simple chat. AI Code Assistance turns your editor into a specialist across four full areas:

• General coding — explain, refactor, generate, fix code in any language
• Data analytics — inventory datasets, frame business questions, drill into root causes, generate decks
• Data Science — clean, EDA, build/train/tune ML models, explain them with SHAP/LIME
• AI Engineering — production RAG, prompt engineering, LoRA fine-tuning, LLM evaluation, agents

Powered by a local backend (a small FastAPI router you run on your machine) that talks directly to the model provider of your choice — bring your own keys for OpenRouter, OpenAI, Groq or Gemini, or run fully local with Ollama / LM Studio. No Colab, no tunnel, no third-party server in the middle.

The assistant responds in whatever language you write in — English, Portuguese, Italian, Spanish, French, or any other. Just type naturally.

Architecture

   ┌──────────────────────┐          ┌──────────────────────┐        ┌──────────────────┐
   │ VS Code (you)        │  HTTP/   │ Local backend        │  HTTPS │ Provider          │
   │  ┌────────────────┐  │  SSE     │ (FastAPI router on   │ ─────▶ │ OpenRouter/OpenAI │
   │  │ AI Code chat   │◄─┼──────────┼─ 127.0.0.1:8001)     │        │ Groq/Gemini  …or… │
   │  └────────────────┘  │          │  role-based routing  │ ─────▶ │ Ollama / LM Studio│
   │  - 14 slash skills   │          │  per-task model cfg  │        │ (local, no key)   │
   │  - Tool calling      │          └──────────────────────┘        └──────────────────┘
   │  - Voice + vision    │
   └──────────────────────┘

Each task type (planner / coder / vision / general / agentic) routes to whatever model you assigned it. Tools execute only on your machine — the backend just emits intents.

What you can do — the four areas

🧑‍💻 General coding (works everywhere)

• Open Chat: dedicated sidebar chat with an AI Code Assistance icon in the Activity Bar (same UX as Copilot Chat / Claude Code). Click and use, no setup ritual.
• Inline commands:
  • AI Code Assistance: Explain Selection (Ctrl+Alt+E)
  • AI Code Assistance: Refactor Selection (Ctrl+Alt+R)
  • AI Code Assistance: Generate at Cursor
• Tool calling: the model can read/write files, run bash, grep, glob, fetch the web, etc. Every tool call shows a confirmation modal with Accept / Always / Deny. Dangerous bash patterns (rm -rf /, dd, fork bombs) block the "Always" option as a safety net.
• MCP support: connect any MCP server via .mcp.json in your workspace root — both stdio and HTTP transports supported.
• Voice input and image attachments for vision-capable models.
• Persistent chat history across sessions.
• Multilingual: responds in the language you write in — no configuration needed.

📊 Data analytics — /explore, /question, /chart, /drill, /report

🔬 Data Science (ML) — /engineer, /eda, /model, /explain

🤖 AI Engineering — /rag, /prompt, /finetune, /eval, /agent

Type /skills or /help in the chat to list all 14 with descriptions.

Choose which model runs each task

AI Code Assistance routes every request to one of five roles — planner, coder, vision, general, agentic — and you decide which model each role uses. Three interchangeable ways, all sharing one config file and hot-reloaded with no restart:

• ⚙️ Configure Models panel (AI Code Assistance: Configure Models) — a panel with a model dropdown per task, a token field per provider (saved to your local .env, never shared), and base-URL fields for Ollama / LM Studio.
• Chat commands — /models to see assignments, /model coder openrouter qwen/qwen-2.5-coder-32b-instruct to pin one, /model now <provider> <model> to force a model for the current chat.
• Edit ai-code-assistance.models.json by hand. It holds only model names (no secrets), so you can commit and share it; teammates add their own keys.

Quick start

1. Install — search AI Code Assistance in the Extensions panel (Ctrl+Shift+X).

2. Run the backend locally (from the project repo):

   cp .env.example .env          # set AI_TOKEN + at least one provider key
   uvicorn backend.main:app --host 127.0.0.1 --port 8001
   

3. Configure VS Code — open Settings (Ctrl+,) and search AI Code Assistance:

   • aiCodeAssistance.backendUrl → http://127.0.0.1:8001
   • aiCodeAssistance.token → the AI_TOKEN from your .env

4. Click the AI Code Assistance icon in the Activity Bar (left rail) — the chat opens in the sidebar.

5. Type /skills to see everything you can do, and click the ⚙️ to pick your models.

Settings

MCP Servers

Create a .mcp.json file at your workspace root to connect external MCP servers:

{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["-y", "@my-org/mcp-server"],
      "env": { "API_KEY": "your-key-here" }
    },
    "http-server": {
      "url": "http://localhost:3000/mcp",
      "headers": { "Authorization": "Bearer TOKEN" }
    }
  }
}

The ⚙️ Configure Models panel shows active MCP servers and has an "Edit .mcp.json" button.

Keybindings

Privacy & security

• Tools require explicit per-session approval. "Always" decisions live in RAM and reset when VS Code closes.
• Token is machine-scoped — does not sync across devices via Settings Sync.
• The backend runs on your own machine and calls your own provider account with your own keys. No third-party server in the middle. Provider keys live in your local .env (gitignored) — never in the shareable model config.
• File system access and shell execution happen only on your machine — the backend just forwards the model's intent.

Why this stack?

• Your models, your bill. Mix cloud (OpenRouter / OpenAI / Groq / Gemini) and local (Ollama / LM Studio) per task.
• Right model per task. A cheap fast model for general chat, a strong coder for code, a vision model for screenshots — configured independently.
• Shareable, secret-free config. The model config file carries model choices; teammates plug in their own keys.
• Editor stays local. All file I/O and shell execution happen on your machine, behind a permission prompt.
• Multilingual. The assistant responds in the language you write in, automatically.

Limitations

• You run the backend yourself (a single uvicorn command) and supply at least one provider key, or a local engine (Ollama / LM Studio). The extension does not include hosted inference.
• AI Engineering skills generate code; they don't run training/RAG/eval pipelines for you. They tell you what to write and why.

Issues & contributing

Bug reports, feature requests, and PRs are welcome at github.com/mendesalex89/AI_Assistant.

License

MIT — see LICENSE.