NIM Code

AI coding assistant for VS Code, powered exclusively by NVIDIA NIM.

Chat, explain, refactor, and fix code with state-of-the-art models — all routed through a single NVIDIA API key. Switch between Llama, Qwen, DeepSeek, Nemotron, and more without leaving your editor.

Features

Multi-model chat

Pick any NVIDIA NIM model from the dropdown. Add your own model IDs through the + button — no extension update required.

Agent mode

Let NIM Code act autonomously on your workspace. It reads, searches, writes, and refactors files; runs terminal commands; queries git; and opens files directly in your editor.

12 built-in agent tools:

Slash commands

Type / in the chat input to trigger context-aware prompts using your active editor selection:

Streaming responses

Responses stream token-by-token so you see output immediately, with full cancel support mid-stream.

Secure API key storage

Your NVIDIA NIM API key is stored in the OS keychain via VS Code SecretStorage — never in settings files or workspace storage.

Persistent sessions

All conversations are saved locally and accessible from the session list (☰). Rename, delete, or switch between sessions at any time.

Quick Start

1. Get an NVIDIA NIM API key

1. Sign up at build.nvidia.com
2. Go to API Keys → Generate Personal Key
3. Copy the key (starts with nvapi-)

2. Install NIM Code

Search "NIM Code" in the Extensions panel (Ctrl+Shift+X) or install from the VS Code Marketplace.

3. Set your API key

Open the Command Palette (Ctrl+Shift+P / Cmd+Shift+P) and run:

NIM Code: Set NVIDIA NIM API Key

Paste your nvapi-… key when prompted.

4. Start chatting

Click the N icon in the Activity Bar, or press Ctrl+Shift+N / Cmd+Shift+N.

Agent Mode

Switch the mode toggle in the chat input to ⚡ Agent. NIM Code will plan and execute multi-step tasks autonomously, showing each tool call as it runs.

Example prompts:

• "Search for all TODO comments in .ts files and fix them one by one"
• "Run pnpm run lint, find the errors with get_diagnostics, and fix them all"
• "Show me git_diff, then write a conventional commit message for these changes"
• "Read src/api/users.ts, add Zod input validation, and open the file when done"
• "List all .test.ts files, find untested functions with search_codebase, and write the missing tests"

Tip: Use 💬 Chat mode for questions and explanations. Use ⚡ Agent for tasks that require reading or changing files.

Supported Models

NIM Code comes with one curated model. Add any model from build.nvidia.com via the + button or Settings → NIM Code → customModels — no extension update needed.

Popular models to add via customModels:

Commands & Keyboard Shortcuts

All commands are also accessible via the Command Palette (Ctrl+Shift+P / Cmd+Shift+P) — search "NIM Code".

Configuration

Open Settings (Ctrl+,) and search "NIM Code", or edit settings.json:

{
  // Base URL for the NVIDIA NIM API — change for on-premise deployments
  "nimcode.baseUrl": "https://integrate.api.nvidia.com/v1",

  // Default model for new sessions
  "nimcode.defaultModel": "meta/llama-3.1-8b-instruct",

  // Per-request timeout in milliseconds (default: 120 000 = 2 min)
  // Increase to 300 000 for reasoning models like DeepSeek R1
  "nimcode.requestTimeoutMs": 120000,

  // Automatic retry attempts on transient errors (0–5)
  "nimcode.maxRetries": 2,

  // Sampling temperature — lower = more deterministic (0–2)
  "nimcode.temperature": 0.2,

  // Additional models shown in the picker
  "nimcode.customModels": [
    {
      "id": "meta/llama-3.3-70b-instruct",
      "label": "Llama 3.3 70B",
      "contextWindow": 128000,
      "capabilities": ["chat", "tools"]
    }
  ]
}

On-premise / self-hosted NIM

"nimcode.baseUrl": "http://localhost:8000/v1"

Everything else — API key, model IDs, streaming, tool use — works identically against a local NIM deployment.

Moving the Panel to the Right Sidebar

NIM Code opens in the left Activity Bar by default. To place it on the right (like GitHub Copilot Chat):

1. Right-click the N icon in the Activity Bar
2. Select Move to Secondary Side Bar

VS Code remembers this permanently.

Privacy & Security

Troubleshooting

"Set your NVIDIA NIM API key to start" banner Run NIM Code: Set NVIDIA NIM API Key from the Command Palette.

Slow or no response with reasoning models (DeepSeek R1, Nemotron) Increase nimcode.requestTimeoutMs to 300000 in Settings — reasoning models can take several minutes on complex prompts.

Rate limit errors NIM Code retries automatically with exponential backoff. Persistent errors indicate you have reached your NVIDIA NIM free-tier limit.

search_codebase fails NIM Code uses VS Code's bundled ripgrep (rg) binary — no separate installation is needed.

Agent writes unexpected content Use 💬 Chat mode with /review first to validate the model understands your codebase before switching to ⚡ Agent.

Requirements

• VS Code 1.90.0 or later
• An NVIDIA NIM API key (free tier available)
• Node.js 20+ (development only)

Contributing

Bug reports and feature requests: GitHub Issues

See ROADMAP.md for the planned feature roadmap and gap analysis.

Local development

git clone https://github.com/vijayjanakiraman/nim-code
cd nim-code
pnpm install        # install all dependencies
pnpm run build      # compile extension + webview
# Press F5 in VS Code to launch the Extension Development Host

For incremental development, run these in two separate terminals:

pnpm run watch:webview      # Vite --watch for the React UI
pnpm run watch:extension    # esbuild --watch for the extension host

Scripts

License

MIT © 2026 Vijay