Self-Host Void Editor: Open Source Cursor Fork 2026

TL;DR

Void Editor is an open-source VS Code fork that adds AI coding features — inline edits, chat, autocomplete, and agent mode — without routing your code through Cursor's proprietary servers. You bring your own LLM: connect to OpenAI, Anthropic Claude, Google Gemini, Groq, or run a local model via Ollama for completely private coding assistance. Backed by YC (YC W25), Void is in active beta with Linux and macOS releases available.

Key Takeaways

• Void Editor: VS Code fork + AI features, open-source (Apache 2.0)
• No middleman: your code goes directly from Void to your chosen LLM provider — no Cursor/Windsurf backend
• Any LLM: OpenAI, Anthropic, Gemini, Groq, Ollama (local), LM Studio, any OpenAI-compatible endpoint
• Cursor $20/month saved: Void is free, you only pay for API tokens you use
• Full VS Code compatibility: all VS Code extensions work in Void
• Features: inline editing, chat panel, autocomplete, agent mode (codebase changes)
• Status (2026): Beta — Linux and macOS available, Windows in progress
• YC-backed: Glass Devtools, W25 batch

---

Why Void Over Cursor?

Cursor is the dominant AI code editor in 2026. It's genuinely excellent. The reasons to consider Void instead:

Privacy concerns with Cursor:
  - Your code is sent to Cursor's servers before reaching the LLM
  - Cursor's privacy mode exists but is limited
  - Cursor controls which models you access and at what cost
  - $20/month regardless of actual usage

Void's approach:
  - Your code goes directly to OpenAI/Anthropic/Ollama — no Void intermediary
  - Complete privacy when using Ollama (everything stays on your machine)
  - Pay-per-token with OpenAI/Anthropic (often cheaper for light users)
  - Free for heavy users who run local models
  - Full source code visibility — audit exactly what data is sent where

---

Void vs. Cursor vs. Other Alternatives

Feature	Void	Cursor	Continue.dev	Aider
Price	Free	$20/month	Free	Free
Open Source	✅ Apache 2.0	❌	✅ Apache 2.0	✅ Apache 2.0
VS Code fork	✅	✅	❌ (extension)	❌ (CLI)
Local LLM (Ollama)	✅	⚠️ Limited	✅	✅
Inline editing	✅	✅	✅	✅
Chat panel	✅	✅	✅	✅
Agent mode	✅	✅	✅	✅
Autocomplete	✅	✅	✅	❌
Codebase indexing	✅	✅	✅	✅
Direct LLM connection	✅	❌	✅	✅
Windows support	In progress	✅	✅	✅

---

Installation

macOS

# Download from voideditor.com (direct LLM connection, no tracking)
# Or via Homebrew (when available):
brew install --cask void

# Current: download the .dmg from https://voideditor.com
# Mount and drag to Applications folder

Linux

# Download the latest .deb or .AppImage from GitHub releases:
# https://github.com/voideditor/void/releases

# Debian/Ubuntu (.deb):
wget https://github.com/voideditor/void/releases/latest/download/void_*.deb
sudo dpkg -i void_*.deb

# AppImage (universal Linux):
wget https://github.com/voideditor/void/releases/latest/download/Void_*.AppImage
chmod +x Void_*.AppImage
./Void_*.AppImage

# Arch Linux (AUR):
yay -S void-editor-bin

Build from Source

# Requirements: Node.js 18+, Python 3, Git, C++ build tools

git clone https://github.com/voideditor/void.git
cd void

# Install dependencies
npm install

# Build for your platform
npm run compile

# Launch
./scripts/code.sh          # Linux/macOS

---

Configuring Your LLM Provider

Void's model configuration is in Settings → Void Settings:

OpenAI

{
  "void.models": [
    {
      "provider": "openai",
      "model": "gpt-4o",
      "apiKey": "sk-..."
    },
    {
      "provider": "openai",
      "model": "gpt-4o-mini",
      "apiKey": "sk-..."
    }
  ]
}

Anthropic Claude

{
  "void.models": [
    {
      "provider": "anthropic",
      "model": "claude-opus-4-5",
      "apiKey": "sk-ant-..."
    },
    {
      "provider": "anthropic",
      "model": "claude-sonnet-4-5",
      "apiKey": "sk-ant-..."
    }
  ]
}

Ollama (Fully Local, Zero Cost)

# 1. Install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# 2. Pull a coding model
ollama pull deepseek-coder-v2:16b    # Best for code, 16B params
ollama pull qwen2.5-coder:7b         # Good balance, 7B params
ollama pull codellama:13b            # Meta's coding model

# 3. Configure Void to use Ollama

{
  "void.models": [
    {
      "provider": "ollama",
      "model": "deepseek-coder-v2:16b",
      "endpoint": "http://localhost:11434"
    }
  ]
}

With Ollama configured, your entire coding workflow stays local — no tokens, no API bills, no data leaving your machine.

Groq (Fast Free Tier)

{
  "void.models": [
    {
      "provider": "groq",
      "model": "llama-3.3-70b-versatile",
      "apiKey": "gsk_..."
    }
  ]
}

Groq's free tier offers 14,400 requests/day at very high speed (tokens generated at 500+ tokens/second) — effectively free for most individual developers.

---

Core Features

Inline Editing (Cmd/Ctrl + K)

1. Select code you want to modify
2. Press Cmd+K (macOS) or Ctrl+K (Linux/Windows)
3. Type your instruction: "Refactor this to use async/await"
4. Void sends: system prompt + file context + selected code + your instruction
   → directly to your configured LLM
5. Diff view shows proposed changes
6. Accept (Tab) or reject (Esc)

Chat Panel (Cmd/Ctrl + L)

1. Open chat sidebar
2. Type your question about the codebase
3. Void automatically includes:
   - Current file context
   - Referenced files (@file syntax)
   - Selected code
4. Direct API call to your LLM
5. Code blocks in response have "Apply" button for one-click insertion

Agent Mode (Multi-File Edits)

1. Describe what you want to build or change
2. Void's agent:
   - Reads relevant files in your codebase
   - Plans required changes across multiple files
   - Executes changes as a series of edits
   - Shows diff of all changes before applying
3. Review and accept/reject the full changeset

---

VS Code Extensions Compatibility

Because Void is a VS Code fork, most VS Code extensions work without modification:

Compatible extensions:
  ESLint, Prettier, GitLens          ✅
  Docker, Kubernetes                 ✅
  Python, Go, Rust Analyzer          ✅
  Tailwind CSS IntelliSense         ✅
  Database clients (SQLite, Postgres) ✅
  Vim/Emacs keybindings             ✅
  GitHub Copilot extension          ⚠️ (redundant but installs)
  Cursor-specific extensions        ❌ (Cursor-proprietary)

---

Migrating from Cursor

Cursor and Void are both VS Code forks. Your settings and keybindings transfer:

# Export Cursor settings
cp ~/Library/Application\ Support/Cursor/User/settings.json ~/cursor-settings-backup.json
cp ~/Library/Application\ Support/Cursor/User/keybindings.json ~/cursor-keybindings-backup.json

# Import into Void (same path structure as VS Code)
cp ~/cursor-settings-backup.json ~/Library/Application\ Support/Void/User/settings.json
cp ~/cursor-keybindings-backup.json ~/Library/Application\ Support/Void/User/keybindings.json

# Install your extensions in Void:
# View → Extensions → search for each extension you use

---

Cost Comparison

Cursor Pro: $20/month = $240/year

Void + OpenAI GPT-4o:
  Light usage (10 code chats/day): ~$5-15/month
  Heavy usage (50+ chats/day):     ~$20-40/month
  (GPT-4o: $2.50/1M input tokens, $10/1M output)

Void + Claude Sonnet:
  Light usage: ~$3-10/month
  Heavy usage: ~$15-30/month
  (Claude Sonnet: $3/1M input, $15/1M output)

Void + Ollama (local Llama 3.3 70B or Qwen 2.5):
  Cost: $0 (existing hardware)
  Hardware requirement: 32GB+ RAM for 70B models
                        16GB RAM for 7B-13B models

Break-even vs. Cursor Pro:
  Light user: Void + cloud API is CHEAPER (~$5-15/month)
  Heavy user: Void + cloud API is ~SAME ($20-40/month)
  Local models: Void is ALWAYS cheaper after hardware cost

---

Current Limitations (Beta Status)

Windows: Not yet available (macOS and Linux only as of 2026)
Stability: Beta — occasional crashes, reported in GitHub issues
Auto-complete quality: Good but below Cursor's fine-tuned models
Agent mode: Functional but less polished than Cursor's Composer
No Void Cloud: Everything is self-configured (advantage for privacy, work for setup)

Void is the best option for privacy-focused developers who want full control over their LLM stack. For teams where Windows is primary or who want a polished out-of-the-box experience, Cursor is still the smoother option in 2026.

---

More open-source AI coding tools at OSSAlt.

Related: Best Open Source Cursor Alternatives 2026 · Self-Host Perplexica