# devvm — AI Coding Tool Review & Pricing

> devvm is an open-source Go CLI that gives each project folder its own isolated virtual machine for you or a coding agent. Running `devvm` in a folder detects the toolchains the project needs, mounts only that folder at the same path, and opens a shell in the VM where Claude Code, Codex, opencode or pi can run without touching the host.

Source: https://ai.dosa.dev/tools/devvm · Updated Nov 10, 2026 · Category: Developer Productivity & Workflow · Published by dosa.dev

## At a glance

- **Tool**: devvm
- **Company**: devvmhq
- **Category**: [Developer Productivity & Workflow](https://ai.dosa.dev/category/productivity)
- **Pricing model**: Open Source
- **Official website**: https://devvm.dev/

## Key features

- One Lima VM per project folder, reopened on the next `devvm` run
- Toolchain detection from project files such as package.json
- Claude Code, Codex, opencode and pi run inside the VM with imported settings, skills and MCP servers
- Allowlist network tier by default, with other network tiers available
- Secrets such as GitHub and Claude Code tokens stay on the host machine
- Built-in docker, nix and desktop layers plus custom layers via `devvm layer new`
- `devvm doctor` checks prerequisites; releases are signed with minisign

## Pricing

**Model**: Open Source

devvm is free and open-source under the MIT license with no paid tiers. It runs VMs locally on Lima, so the only cost is your own machine; coding agents inside the VM use your existing Claude, ChatGPT or provider subscriptions.

## Who it is for

- **Best for**: Developers on macOS or Linux who want to run coding agents in a per-project sandbox to limit the blast radius of supply chain attacks, prompt injections or rogue agent commands.
- **Not ideal for**: Windows users, Intel Mac users (not yet tested), or teams that need cloud-hosted sandboxes and access to many internal services across repositories.

## Verdict

A focused, security-minded way to sandbox local coding agents per project; very new and still at release-candidate stage.

## Recent updates

v0.1.1-rc.2 pre-release published on November 9, 2026, days after the project's public launch on November 6, 2026, which reached 189 points on Hacker News.

## Frequently asked questions

### Is devvm free?

Yes - devvm is Open Source. devvm is free and open-source under the MIT license with no paid tiers. It runs VMs locally on Lima, so the only cost is your own machine; coding agents inside the VM use your existing Claude, ChatGPT or provider subscriptions.

### Is devvm open source?

Yes - devvm is open source. devvm is free and open-source under the MIT license with no paid tiers. It runs VMs locally on Lima, so the only cost is your own machine; coding agents inside the VM use your existing Claude, ChatGPT or provider subscriptions.

### Who is devvm best for?

Developers on macOS or Linux who want to run coding agents in a per-project sandbox to limit the blast radius of supply chain attacks, prompt injections or rogue agent commands.

### Who is devvm not ideal for?

Windows users, Intel Mac users (not yet tested), or teams that need cloud-hosted sandboxes and access to many internal services across repositories.

### What are the best devvm alternatives?

The closest devvm alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.

### Who makes devvm?

devvm is developed by devvmhq. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.

## Top alternatives

- [Pieces for Developers](https://ai.dosa.dev/tools/pieces-for-developers) (Paid) — Developers who work across multiple tools, IDEs, and environments and need to maintain a persistent, searchable history of code snippets, research, and workflow context.
- [agenttrace](https://ai.dosa.dev/tools/agenttrace) (Open Source) — Developers and teams needing to monitor and debug the efficiency, cost, and health of AI coding agents across multiple workflows.
- [Vibe Kanban](https://ai.dosa.dev/tools/vibe-kanban) (Open Source) — Software engineers who use multiple AI coding agents and need a structured environment to manage, plan, and review their output in parallel.
- [ai-memory](https://ai.dosa.dev/tools/ai-memory) (Open Source) — Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions.
- [smolvm](https://ai.dosa.dev/tools/smolvm) (Open Source) — Running isolated coding agent sandboxes, untrusted code, and persistent local development environments that require a real Linux kernel boundary.
- [coop](https://ai.dosa.dev/tools/coop) (Open Source) — Running autonomous AI coding agents that require broad system access while maintaining a strong security boundary for the host machine.
- Full alternatives guide: https://ai.dosa.dev/tools/devvm/alternatives