Armorer

Local control plane for AI agents

Run native Armorer Flue agents with local sandboxes, guided setup, credential handling, guardrails, approvals, jobs, logs, and runtime health in one place.

Run any agent. Securely. Local-first by default.

Experimental release candidate: Armorer is under active development. The current release train is intended for early testers who are comfortable with local agent runtimes, Docker/Colima, and rapidly evolving setup flows.

Website · Install · Docs for humans · Issues

Star ArmorerLabs/Armorer if you want safer local agent runtimes to exist.

---

Develop the OSS control plane

curl -fsSL https://armorerlabs.com/install | sh -s -- --dev

Or run the workspace manually:

corepack enable
pnpm install --frozen-lockfile
pnpm build
pnpm test
pnpm typecheck
pnpm --filter armorer-ui-selfhost build

pnpm test is the credential-free OSS suite. Authorized private integration environments additionally run pnpm test:private with a compatible Vault runtime.

Runtime use also needs Rust/Cargo for the native Armorer gateway and authorized access to the private Armorer Vault runtime. Set ARMORER_VAULT_BIN to a compatible private artifact, or set ARMORER_VAULT_SOURCE_DIR to a separate private ArmorerLabs/Armorer-Vault checkout. pnpm dev, pnpm start, and the CLI run fail-closed Vault preflights. OSS builds and tests never download or package a private runtime.

Production appliances and proprietary products are distributed only through authenticated private channels, not this public repository or its releases. See Private distributions.

Start the self-hosted UI from source:

pnpm dev -- --hostname 0.0.0.0 --port 3099

Then open http://127.0.0.1:3099.

Use the CLI directly from the workspace:

pnpm armorer -- list
pnpm armorer -- core status
pnpm armorer -- install armorer-agent --alias signal-native --yes --skip-scan
pnpm armorer -- jobs list

Armorer also supports native Armorer-managed agents and Vault-backed connected apps from the same CLI:

pnpm armorer -- install armorer-agent --alias signal-native --yes --skip-scan
pnpm armorer -- connections list
pnpm armorer -- linear customer-sync list

For docker build GPG signature failures or proxy issues during agent installation, see the Troubleshooting guide.

Use Your Agent

Set up Armorer from https://github.com/ArmorerLabs/Armorer on this machine.
Follow AGENTS.md and the repository instructions.
Install Armorer, verify Docker, start the local UI, then help me create and configure an Armorer Flue agent.
Do not report success until the Armorer CLI works, the UI is reachable, and runtime health checks pass.

Why Armorer

Running agents directly	Running agents through Armorer Labs
Each agent has its own setup path	One local control plane
Credentials are easy to scatter	Guided credential handling
Risky actions are hard to review	Human approvals and guardrails
Logs live wherever the agent puts them	Jobs, runtime status, and audit trails
Local networking gets messy	Local-first with optional private remote access

What Exists Today

• Local agent runtime and UI.
• Docker sandbox orchestration for installed agents.
• Guided setup for providers, models, credentials, channels, and skills.
• Native Armorer Flue agents as the supported agent runtime.
• Armorer Agent chat runs with durable Flue-backed run state and live workstream visibility.
• Vault-backed connected apps with explicit per-agent grants.
• Linear CRM/customer sync queues with approval-aware writes.
• Guardrails for suspicious inputs, leaked credentials, and risky actions.
• Jobs, logs, runtime health, and setup state in one operator surface.

For operator workflows, see Usage. For native-agent acceptance criteria, see ARM-160 Native Agent Success Contract.

Humans

Prefer doing it yourself instead of handing the repo to an agent?

Start here: HUMANS.md

Positioning

Armorer Labs is not another model provider. It is not a hosted agent platform. It is a self-hosted, local-first agent runtime layer for builders who want control, sandboxing, and security posture before they scale agent usage.