aicoolies logo
Void logo
Void logo

Void

Open-source AI code editor focused on privacy

open sourceupdated Apr 21, 2026

Open-source AI code editor with zero data retention and direct API connections. Supports local models via Ollama and LM Studio, ensuring complete privacy over your code. Built as a VS Code fork with agent mode and MCP support, offering the familiar VS Code experience while giving developers full control over which AI models they use and where their data goes.

Void is an open-source, AI-powered code editor built as a fork of Visual Studio Code that prioritizes privacy, transparency, and developer freedom. It addresses concerns about proprietary AI code editors that route code through private backend servers by allowing developers to connect directly to any AI model provider or run models locally without intermediaries. Developed by YC-backed startup Glass Devtools, Void offers the familiar VS Code experience enhanced with AI capabilities while keeping developers in complete control of their data.

Void includes AI autocomplete via the Tab key, inline code editing with contextual suggestions, and multiple interaction modes including Agent Mode for autonomous multi-step tasks, Gather Mode for collecting information, and standard chat for conversational coding assistance. The editor supports direct connections to OpenAI, Anthropic, Google Gemini, Ollama, and other model providers, eliminating the privacy concerns of routing code through third-party servers. All traditional VS Code features including extensions, themes, and keybindings are fully supported, providing a seamless migration path for existing VS Code and Cursor users.

Void is designed for privacy-conscious developers, enterprises with strict data governance requirements, and open-source enthusiasts who want full transparency in their development tools. It appeals to developers who want AI assistance but are uncomfortable with proprietary solutions that may use their code for training or route sensitive codebases through external servers. The editor reached Beta v1.0.0 in June 2025, though the team has since paused feature development on the IDE to explore novel coding paradigms, making it best suited for developers comfortable with early-stage open-source tools.

Pricing

Free (open-source, bring your own API key)

Platforms

macOS, Windows, Linux

Categories

Tags

Use Cases

Related Tools

computed discovery: shared active categories · kept separate from editor-verified Alternatives

Cursor logo

Cursor

Top Pick

The AI-first code editor

AI-first code editor built as a VS Code fork that deeply integrates LLMs into every part of the development workflow. Features Tab autocomplete with multi-line predictions, Cmd+K inline editing, AI chat with full codebase awareness, and Agent mode for autonomous multi-file edits with terminal execution. Supports GPT-4, Claude, and more with automatic context from project files and docs. Includes privacy mode for SOC 2 compliance. The leading AI-native IDE with 100K+ paying users.

freemiumTelemetry
Google Antigravity logo

Google Antigravity

Top Pick

Agent-first development platform from Google with desktop app and CLI

Google Antigravity is Google's AI-powered agentic development platform, announced in November 2025 and expanded with Antigravity 2.0 at I/O 2026, that places autonomous AI agents at the center of software development. Distributed as both a VS Code-based desktop app and the new Antigravity CLI, it runs planning, implementation, and verification agents — backed by Gemini 3.1 Pro/Flash, Claude Sonnet/Opus 4.6, and GPT-OSS 120B — across editor, terminal, and browser.

freemiumTelemetry
Orca ADE logo

Orca

The Agent Development Environment for running parallel coding agents in isolated worktrees

Orca is an open-source Agent Development Environment (ADE) for running 25+ coding agents in parallel, each in an isolated git worktree. Supports Claude Code, Codex, Gemini, OpenCode, Amp, Goose, Grok, and Aider with BYOK subscriptions. Includes a WebGL terminal with infinite splits, built-in git tracking, hot-swap accounts, and an iOS/Android companion app for monitoring agent work on the move.

Open Source
Open Agents logo

Open Agents

Fork, customize, and ship AI agents on Vercel in minutes

Open Agents is a Vercel Labs open-source template for building and deploying cloud-hosted AI agents. It provides a production-ready Next.js starter with built-in tool use, streaming responses, multi-model support, and deployment on Vercel infrastructure. Developers can fork, customize agent behavior and tools, then ship agent-backed apps in minutes with automatic scaling and edge routing.

freeOpen Source
Magentic-UI logo

Magentic-UI

Human-in-the-loop web agent you can co-pilot in real time

Magentic-UI is a Microsoft Research web agent with a human-in-the-loop interface for browsing, coding, and file tasks. It plans multi-step actions, asks for approval before executing, and lets users co-pilot by taking over the browser mid-task. Built on AutoGen, it runs a team of specialized agents for web browsing, file handling, and code execution with full action transparency and safety guardrails.

freeOpen Source
Guidance logo

Guidance

Constrained generation that guarantees valid LLM outputs every time

Guidance is Microsoft's structured generation library that enforces output constraints directly within LLM decoding. It supports JSON schemas, regex patterns, grammars, and interleaved generation-and-control flow to guarantee valid outputs from any compatible model. Works with local models via llama.cpp, Transformers, and remote APIs including OpenAI and Anthropic. Eliminates retry loops and post-processing for structured data extraction.

freeOpen Source

Comparisons

PearAI vs Void Editor: Active Open-Source IDE or Deprecated Local-First Reference?

PearAI offers an active, source-visible AI IDE path, while Void is officially deprecated, no longer accepts contributions, and has an archived repository. Both projects appeal to developers who value open implementations and provider choice, but only PearAI retains a credible upstream direction. PearAI is the winner for new adoption; Void should be treated as reference code or a fork requiring independent maintenance.

PearAIVoid

Cursor vs Void Editor: Maintained Agent Platform or Deprecated Local-First IDE?

Cursor is an actively maintained commercial agent platform; Void is officially deprecated, no longer accepting contributions, and its repository is archived. This comparison treats Void’s local-first and open-source features as historical capabilities, not a current roadmap. Cursor wins because it provides maintained editor, cloud, remote, review, and team workflows for ongoing development.

CursorVoid

FAQ

What is Void?

Open-source AI code editor with zero data retention and direct API connections. Supports local models via Ollama and LM Studio, ensuring complete privacy over your code. Built as a VS Code fork with agent mode and MCP support, offering the familiar VS Code experience while giving developers full control over which AI models they use and where their data goes.

Is Void free?

Yes — Void is open source and free to use. Free (open-source, bring your own API key)

Is Void open source?

Yes — Void is open source.

What are the best Void alternatives?

The top editor-verified Void alternatives are Trae, PearAI.