cd /news/ai-agents/brig-run-coding-agents-in-a-microvm-… · home topics ai-agents article
[ARTICLE · art-129984] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Brig: Run coding agents in a MicroVM sandbox

Brig, a tool from the brig-sh project, runs coding agents inside a microVM sandbox on the user's own machine, starting a session with the command `brig run claude ~/code/demo`. The sandbox boots with no credentials, mounts a named project read-write at `/work/<name>`, and excludes all other host directories, the keychain, and the SSH agent, with egress policy enforced only on hull's `hvi` backend. Brig requires macOS 15 or newer on Apple silicon Macs, or macOS 14 with `BRIG_HYPERVISOR=vz`, and supports Linux x86-64 or arm64 with `nerdctl`, containerd and the `urunc` shim; Intel Macs are not supported.

read4 min views9 publishedSep 15, 2026
Brig: Run coding agents in a MicroVM sandbox
Image: Michielbdejong (auto-discovered)

Brig runs a coding agent inside a microVM on your own machine.

An agent working unattended can only damage what you handed it. Point it at one project, and a bad edit or a bad command reaches no further than that project. When you are done, throw the sandbox away and start clean.

One command starts a sandbox and runs the agent in it:

brig run claude ~/code/demo

A session is <agent> or <agent>@<label>, the ref every command takes. claude and claude@refactor are two independent sessions of the same agent, each with its own sandbox. The guest home is the host directory holding a session's settings and history. claude resolves to the claude-code agent, so its guest home is ~/brig/claude-code, and claude@refactor's is the sibling ~/brig/claude-code-refactor, not a directory inside it.

Name a project on the run line, and Brig mounts it read-write at /work/<name>, where the agent starts. Credentials reach the guest only when you deliver them: the sandbox boots with none, and the agent asks you to log in. What the guest does not get: every other host directory, your keychain, and your SSH agent. docs/sessions.md is the full model.

Host Supported
Mac, Apple silicon, macOS 15 or newer Yes
Mac, Apple silicon, macOS 14 Yes, with BRIG_HYPERVISOR=vz
Intel Mac No
Linux, x86-64 or arm64 Yes, with nerdctl , containerd and theurunc shim

macOS 15 is the floor: six of the eight built-in profiles need the hvi backend. See docs/install.md#platform-support for the rest.

brew tap brig-sh/brig
brew trust brig-sh/brig
brew install --cask brig

The cask brings hull and cosign with it. For install.sh, Linux, or a source build, see docs/install.md.

brig doctor

Each line is a check. A !! line prints its fix beside it.

mkdir -p ~/code/demo
brig run claude ~/code/demo

Brig prints brig: image and boot assets verified, Claude Code asks you to log in inside the sandbox, and pwd inside the agent prints /work/demo. The first run pulls the guest image and the boot assets, so it is slow. docs/authentication.md covers the login and how to carry one in from the host.

brig stop claude    # stop the sandbox, keep its name
brig rm claude      # stop it and remove it

Neither touches ~/brig/claude-code or ~/code/demo. docs/quickstart.md walks through all of this, explained.

The project mount is read-write, and those are your real files: the agent can change anything under it. On the default shared network the agent reaches the internet, so anything it can read it can also send. Brig enforces egress policy only on hull's hvi backend, and refuses a policy-bound run on any other backend rather than run it unenforced. Image verification defaults to warn, which reports an unverifiable image and boots it anyway. Set BRIG_VERIFY=require to refuse one instead. docs/security.md has the full picture.

If you want to Read
Install Brig on any supported host docs/install.md
Get a first agent running, step by step docs/quickstart.md
Understand homes, projects and sessions docs/sessions.md
Log an agent in, or give it Git access docs/authentication.md ,docs/secrets.md
Look up a command, a flag or a variable docs/cli.md
Run your own agent or your own image docs/profiles.md ,docs/guest-image.md
Restrict what the guest can reach docs/policies.md
Understand the isolation, and its limits docs/security.md
Know what Brig counts, and turn it off docs/telemetry.md
Fix something that went wrong docs/troubleshooting.md
Move off a retired command spelling docs/migration.md
Know what is stable and what is not docs/stability.md

The full index is docs/README.md.

Brig is a prerelease, in the 0.1.0-rc series. brig version prints yours, and docs/stability.md says what you can script against today. docs/support.md says where to ask a question or file a bug, and SECURITY.md is where to report a vulnerability instead of a public issue. CONTRIBUTING.md covers the build, the tests and the review norms, and AI_POLICY.md says how AI-assisted contributions are handled. Brig ships under the Apache License 2.0. See LICENSE.

Brig itself counts nothing. On macOS the hull runtime it drives counts a few events, and on Linux nothing is sent. brig telemetry status shows the current setting, and brig telemetry off turns it off. docs/telemetry.md has the field-by-field detail.

── more in #ai-agents 4 stories · sorted by recency
── more on @brig 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/brig-run-coding-agen…] indexed:0 read:4min 2026-09-15 ·