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.

Why Self-Host Void Editor?

The case for self-hosting Void Editor comes down to three practical factors: data ownership, cost at scale, and operational control.

Data ownership is the fundamental argument. When you use a SaaS version of any tool, your data lives on someone else's infrastructure subject to their terms of service, their security practices, and their business continuity. If the vendor raises prices, gets acquired, changes API limits, or shuts down, you're left scrambling. Self-hosting Void Editor means your data and configuration stay on infrastructure you control — whether that's a VPS, a bare metal server, or a home lab.

Cost at scale matters once you move beyond individual use. Most SaaS equivalents charge per user or per data volume. A self-hosted instance on a $10-20/month VPS typically costs less than per-user SaaS pricing for teams of five or more — and the cost doesn't scale linearly with usage. One well-configured server handles dozens of users for a flat monthly fee.

Operational control is the third factor. The Docker Compose configuration above exposes every setting that commercial equivalents often hide behind enterprise plans: custom networking, environment variables, storage backends, and authentication integrations. You decide when to update, how to configure backups, and what access controls to apply.

The honest tradeoff: you're responsible for updates, backups, and availability. For teams running any production workloads, this is familiar territory. For individuals, the learning curve is real but the tooling (Docker, Caddy, automated backups) is well-documented and widely supported.

Server Requirements and Sizing

Before deploying Void Editor, assess your server capacity against expected workload.

Minimum viable setup: A 1 vCPU, 1GB RAM VPS with 20GB SSD is sufficient for personal use or small teams. Most consumer VPS providers — Hetzner, DigitalOcean, Linode, Vultr — offer machines in this range for $5-10/month. Hetzner offers excellent price-to-performance for European and US regions.

Recommended production setup: 2 vCPUs with 4GB RAM and 40GB SSD handles most medium deployments without resource contention. This gives Void Editor headroom for background tasks, caching, and concurrent users while leaving capacity for other services on the same host.

Storage planning: The Docker volumes in this docker-compose.yml store all persistent Void Editor data. Estimate your storage growth rate early — for data-intensive tools, budget for 3-5x your initial estimate. Hetzner Cloud and Vultr both support online volume resizing without stopping your instance.

Operating system: Any modern 64-bit Linux distribution works. Ubuntu 22.04 LTS and Debian 12 are the most commonly tested configurations. Ensure Docker Engine 24.0+ and Docker Compose v2 are installed — verify with docker --version and docker compose version. Avoid Docker Desktop on production Linux servers; it adds virtualization overhead and behaves differently from Docker Engine in ways that cause subtle networking issues.

Network: Only ports 80 and 443 need to be publicly accessible when running behind a reverse proxy. Internal service ports should be bound to localhost only. A minimal UFW firewall that blocks all inbound traffic except SSH, HTTP, and HTTPS is the single most effective security measure for a self-hosted server.

Backup and Disaster Recovery

Running Void Editor without a tested backup strategy is an unacceptable availability risk. Docker volumes are not automatically backed up — if you delete a volume or the host fails, data is gone with no recovery path.

What to back up: The named Docker volumes containing Void Editor's data (database files, user uploads, application state), your docker-compose.yml and any customized configuration files, and .env files containing secrets.

Backup approach: For simple setups, stop the container, archive the volume contents, then restart. For production environments where stopping causes disruption, use filesystem snapshots or database dump commands (PostgreSQL pg_dump, SQLite .backup, MySQL mysqldump) that produce consistent backups without downtime.

For a complete automated backup workflow that ships snapshots to S3-compatible object storage, see the Restic + Rclone backup guide. Restic handles deduplication and encryption; Rclone handles multi-destination uploads. The same setup works for any Docker volume.

Backup cadence: Daily backups to remote storage are a reasonable baseline for actively used tools. Use a 30-day retention window minimum — long enough to recover from mistakes discovered weeks later. For critical data, extend to 90 days and use a secondary destination.

Restore testing: A backup that has never been restored is a backup you cannot trust. Once a month, restore your Void Editor backup to a separate Docker Compose stack on different ports and verify the data is intact. This catches silent backup failures, script errors, and volume permission issues before they matter in a real recovery.

Security Hardening

Self-hosting means you are responsible for Void Editor's security posture. The Docker Compose setup provides a functional base; production deployments need additional hardening.

Always use a reverse proxy: Never expose Void Editor's internal port directly to the internet. The docker-compose.yml binds to localhost; Caddy or Nginx provides HTTPS termination. Direct HTTP access transmits credentials in plaintext. A reverse proxy also centralizes TLS management, rate limiting, and access logging.

Strong credentials: Change default passwords immediately after first login. For secrets in docker-compose environment variables, generate random values with openssl rand -base64 32 rather than reusing existing passwords.

Firewall configuration:

ufw default deny incoming
ufw allow 22/tcp
ufw allow 80/tcp
ufw allow 443/tcp
ufw enable

Internal service ports (databases, admin panels, internal APIs) should only be reachable from localhost or the Docker network, never directly from the internet.

Network isolation: Docker Compose named networks keep Void Editor's services isolated from other containers on the same host. Database containers should not share networks with containers that don't need direct database access.

VPN access for sensitive services: For internal-only tools, restricting access to a VPN adds a strong second layer. Headscale is an open source Tailscale control server that puts your self-hosted stack behind a WireGuard mesh, eliminating public internet exposure for internal tools.

Update discipline: Subscribe to Void Editor's GitHub releases page to receive security advisory notifications. Schedule a monthly maintenance window to pull updated images. Running outdated container images is the most common cause of self-hosted service compromises.

Troubleshooting Common Issues

Container exits immediately or won't start

Check logs first — they almost always explain the failure:

docker compose logs -f void-editor

Common causes: a missing required environment variable, a port already in use, or a volume permission error. Port conflicts appear as bind: address already in use. Find the conflicting process with ss -tlpn | grep PORT and either stop it or change Void Editor's port mapping in docker-compose.yml.

Cannot reach the web interface

Work through this checklist:

1. Confirm the container is running: docker compose ps
2. Test locally on the server: curl -I http://localhost:PORT
3. If local access works but external doesn't, check your firewall: ufw status
4. If using a reverse proxy, verify it's running and the config is valid: caddy validate --config /etc/caddy/Caddyfile

Permission errors on volume mounts

Some containers run as a non-root user. If the Docker volume is owned by root, the container process cannot write to it. Find the volume's host path with docker volume inspect VOLUME_NAME, check the tool's documentation for its expected UID, and apply correct ownership:

chown -R 1000:1000 /var/lib/docker/volumes/your_volume/_data

High resource usage over time

Memory or CPU growing continuously usually indicates unconfigured log rotation, an unbound cache, or accumulated data needing pruning. Check current usage with docker stats void-editor. Add resource limits in docker-compose.yml to prevent one container from starving others. For ongoing visibility into resource trends, deploy Prometheus + Grafana or Netdata.

Data disappears after container restart

Data stored in the container's writable layer — rather than a named volume — is lost when the container is removed or recreated. This happens when the volume mount path in docker-compose.yml doesn't match where the application writes data. Verify mount paths against the tool's documentation and correct the mapping. Named volumes persist across container removal; only docker compose down -v deletes them.

Keeping Void Editor Updated

Void Editor follows a regular release cadence. Staying current matters for security patches and compatibility. The update process with Docker Compose is straightforward:

docker compose pull          # Download updated images
docker compose up -d         # Restart with new images
docker image prune -f        # Remove old image layers (optional)

Read the changelog before major version updates. Some releases include database migrations or breaking configuration changes. For major version bumps, test in a staging environment first — run a copy of the service on different ports with the same volume data to validate the migration before touching production.

Version pinning: For stability, pin to a specific image tag in docker-compose.yml instead of latest. Update deliberately after reviewing the changelog. This trades automatic patch delivery for predictable behavior — the right call for business-critical services.

Post-update verification: After updating, confirm Void Editor is functioning correctly. Most services expose a /health endpoint that returns HTTP 200 — curl it from the server or monitor it with your uptime tool.

---

More open-source AI coding tools at OSSAlt.

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