NIM Code

AI coding assistant for VS Code, powered 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 Qwen, Kimi, Nemotron, GLM, DeepSeek, and more without leaving your editor.

No API key? Start instantly with Auto mode — 30 free requests per day, no sign-up required.

Features

✦ Auto mode — free tier, no key needed

Start chatting immediately without an NVIDIA API key. Auto mode uses a built-in proxy powered by Llama 3.1 8B via the NIM Code infrastructure.

Note: Auto mode is a Beta feature. For agent tools, file operations, and the full model library, switch to Chat or Agent mode with your own NVIDIA NIM key.

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; runs code reviews; tracks its own progress; and opens files directly in your editor.

16 built-in agent tools:

Right-click code actions

Select any code, then right-click (or press Ctrl+. for the Quick Fix lightbulb) to jump straight into Explain, Fix, Review, Refactor, Generate Tests, or Document — each opens the chat panel with the matching slash command pre-filled using your selection.

MCP (Model Context Protocol) support

Connect your own local MCP servers (stdio transport) via nimcode.mcpServers in Settings. Each server's tools are merged into Agent mode's tool roster, namespaced as mcp__<server>__<tool>, so the agent can call out to your own tools alongside the 16 built-ins. See Configuration.

Tool-call approval & Plan mode

Choose how much confirmation Agent mode needs before acting — Manual, Edit automatically, Auto, or Plan (read-only investigation with no file/shell access) — via the approval-mode dropdown next to the model picker. File writes show a VS Code diff editor to review before applying.

Live agent task list

For multi-step tasks, the agent maintains a visible todo checklist (via the todo_write tool) that updates in place as it works through each step, so you can follow along without reading every tool call.

Reasoning effort control

For reasoning-capable models, pick Low, Medium, or High effort from the dropdown next to the model picker to trade off response speed against depth of reasoning.

Semantic codebase search

Run NIM Code: Index Codebase for Semantic Search from the Command Palette to build a local embedding index of your workspace (via nimcode.embeddingModel). Once built, the agent's search_codebase_semantic tool can find relevant code by meaning, not just keyword — useful for "where do we handle X" style questions.

Image attachments (vision)

Paste a screenshot directly into the chat input to attach it to your message — handy for sharing UI bugs, error dialogs, or design mockups. Requires a model with the vision capability (built-in or added via customModels); up to 4 images per message.

AI-generated commit messages

Click the sparkle icon in the Source Control view's title bar (or run NIM Code: Generate Commit Message) to fill the commit message box with a Conventional Commits message generated from your staged (or working-tree) diff.

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.

Copy code blocks

Every code block in the chat output has a Copy button always visible in the header bar. Click it to copy the code to your clipboard in one click, or use Insert (appears on hover) to paste it directly at the cursor.

Token budget indicator

A context-window usage bar appears below the message list, showing how much of the model's context has been consumed by the current conversation. Color shifts from green → amber → red as you approach the limit.

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

Option A — No API key (Auto mode)

1. Install NIM Code from the VS Code Marketplace.
2. Click the N icon in the Activity Bar (or press Ctrl+Shift+N).
3. The mode toggle defaults to ✦ Auto — start typing and press Enter to send.

You get 30 free requests per day. The counter in the chat bar shows how many remain.

Option B — Full access (Chat & Agent modes)

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.

Modes

Switch modes with the segmented toggle in the chat bar. The mode hint below the toggle summarises the current capabilities.

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.

Tool-call approval modes

The Mode dropdown next to the model picker (visible in Agent mode) controls how much confirmation the agent needs before acting:

When a confirmation is required, NIM Code opens a VS Code diff editor (for file writes) or a prompt describing the action, with Accept/Reject buttons — reject and the agent reports it and adjusts its approach. Plan mode never touches the filesystem or shell; the agent investigates and proposes a plan as text instead.

Supported Models

NIM Code ships with six curated models. 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",

  // Fallback default model, overridden by defaultChatModel / defaultAgentModel
  "nimcode.defaultModel": "qwen/qwen3-next-80b-a3b-instruct",

  // Model selected automatically when Chat mode is active
  "nimcode.defaultChatModel": "qwen/qwen3-next-80b-a3b-instruct",

  // Model selected automatically when Agent mode is active — use a strong tool-use model
  "nimcode.defaultAgentModel": "qwen/qwen3-next-80b-a3b-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,

  // In Agent mode, auto-include the active file (path + cursor snippet) as
  // context when no explicit selection is attached (default: true)
  "nimcode.agentIncludeActiveFile": true,

  // Embedding model used to build the local semantic codebase index
  // ("NIM Code: Index Codebase" command) and the search_codebase_semantic tool
  "nimcode.embeddingModel": "nvidia/nv-embedqa-e5-v5",

  // 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 This banner only appears in Chat or Agent mode. Switch to ✦ Auto mode to start chatting immediately with no key, or run NIM Code: Set NVIDIA NIM API Key from the Command Palette.

Auto mode daily limit reached The 30-request counter resets at midnight UTC. Switch to 💬 Chat mode with your own NVIDIA NIM API key for unlimited usage.

Slow or no response with large models (Nemotron Super 120B, Kimi K2.6) Increase nimcode.requestTimeoutMs to 300000 in Settings — large 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 for Chat and Agent modes (Auto mode requires no key)
• Node.js 20+ (development only)

Contributing

Bug reports and feature requests: vjwarboy13@gmail.com

Local development

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