Control your machines from anywhere —
under a policy they enforce themselves.

RemoteAgent is an AI agent runtime that lives on your computers. It dials out to the remoteagent.online control plane, executes tasks under the device's own policy, and writes every action to a tamper-evident audit log. The brain is in the cloud. The authority is on your machine.

curl -fsSL https://remoteagent.online/install.sh | sh
macOS · Linux · Windows · WSL2 · Raspberry Pi · Docker — client is MIT open source, one runtime dependency
600+ tests Ed25519 device identity hash-chained audit prompt-injection defense zero inbound ports MCP support

An agent you can show to a security team

Most AI agents ask you to hand over a shell and trust them. RemoteAgent inverts the relationship: the device grants capabilities, the policy engine enforces them, and the audit chain proves what happened.

policy.js

Local policy enforcement

Per-tool allow/deny/prompt rules live in ~/.remoteagent/policy.json — the device's authority. The cloud can never widen it. Capability grants intersect; they never union.

sandbox.js

Argv-based shell, no shell strings

Commands are parsed into argv, binaries resolved to realpaths and checked against an allowlist. No curl | sh, no redirects, no globs. Workspace-confined file access.

audit-sign.js

Tamper-evident audit log

Every step is hash-chained and anchored to the cloud. remoteagent audit verify detects tampering — proof you can export to a SIEM or hand to an auditor.

engine

Durable runs that survive restarts

A real state machine: created → planned → running → verifying → succeeded. A side effect is never replayed merely because a process restarted.

loop.js

Prompt-injection separation

Trusted instructions and untrusted tool content never share a context channel. Attack tests live in the repo and run on every commit.

memory.js

Governed memory

Facts and preferences persist with provenance and revocation — and the policy decides what the agent may remember.

How it works

The client dials out. Nothing dials in. Your machine keeps the keys, the policy, and the audit chain.

On your machine

The remoteagent daemon: executes tools, enforces policy, keeps the tamper-evident audit chain, and reports every step to the dashboard.

Egress only. WebSocket to api.remoteagent.online over TLS. No ports opened, no inbound connections, ever.
Endpoint guard. The client refuses to start unless its control plane is HTTPS/WSS, on the remoteagent.online domain (or an explicitly allowlisted host). Fail-closed by design.
BYO brain (Pro). Run reasoning on-device against your own keys — the plane keeps coordinating; it never sees your prompts.

In the cloud

The control plane: task routing, scheduling, the reasoning brain, dashboards, fleet administration, upgrades, and compliance exports.

The brain. All managed reasoning runs server-side at api.remoteagent.online. The client is a thin, secure executor — business logic never ships to devices.
Your keys stay yours. Only your remoteagent.online API key lives on the device (DPAPI on Windows, 0600 on POSIX). No provider keys, ever.
Fleet control. Tenant-scoped policy profiles with revisions and rollback, JIT access grants, staged upgrades, SIEM export.

Runs everywhere you have computers

macOS (launchd) Linux (systemd) Windows (service) WSL2 Raspberry Pi Docker

One installer script, one command, upgrades with checksum verification and dual-named archives for in-place updates from older versions.

Meter the plane, not the tokens

The client is free and MIT. You pay for what the control plane does: scheduling, audit, memory, policy profiles, fleet admin, compliance exports — regardless of whose keys fire the model.

Free

$0
forever
  • 1 device
  • 25 tasks/day
  • 7-day audit retention
  • cloud-routed keys
  • basic chat
MOST POPULAR

Pro

$12
per device / month
  • BYO-key on-device brain
  • unlimited tasks
  • up to 5 devices
  • 90-day audit retention
  • cost-governance dashboard
  • goals · workflows · delegation
  • memory & vector sync

Team

$25
per seat / month
  • everything in Pro
  • fleet policy templates
  • per-agent capability profiles
  • SSO
  • shared audit
  • compliance exports (ISO 27001, GDPR, AI Act, IEC 62443)

Enterprise

Quote
contract
  • on-prem control plane
  • signed releases
  • LTS window
  • SLA & priority support

Looking for remote work? Post a remote job.

RemoteAgent powers remote jobs online: post a job with a policy profile, a worker's agent executes it under the intersection of local and job policy, and the tamper-evident audit log proves what was done — before escrow releases.

Remote jobs →

Questions a buyer asks

Where does the agent actually run?

On your machine. macOS, Linux, Windows, WSL2 or Raspberry Pi. The cloud is the brain and the dashboard; the device is the executor and the enforcer.

What happens if the cloud is unreachable?

Your machine keeps running what policy allows. The daemon reconnects with backoff; local jobs, policies and the audit chain are unaffected by a network outage.

What can the cloud make my agent do?

Only what your policy permits. The capability model intersects cloud requests with device policy — a grant can narrow, never widen. A denied tool is denied, logged, and visible in the dashboard.

How do I prove what it did?

remoteagent audit verify walks the hash chain. Export an evidence bundle for a SIEM, an auditor, or a job escrow release.

Is the client really open source?

Yes — MIT, one runtime dependency, no telemetry you can't turn off. The open core is the trust story; the control plane is the product. Business logic lives server-side and never ships in the client.

Can I use my own LLM keys?

Pro and Team plans: yes — provider.json or RA_PROVIDER_* env vars, on-device reasoning, zero prompts leave the machine. The plane keeps coordinating and auditing either way.

Install in one command

Downloads, verifies checksums, installs remoteagent (with the legacy mona-agent alias), migrates state, and starts the daemon.

curl -fsSL https://remoteagent.online/install.sh | sh

Windows: irm https://remoteagent.online/install.ps1 | iex  ·  Docker: docker run -d remoteagent/agent