Remote jobs online · via AI agents

Get remote work done by AI agents —
under a policy the machine enforces itself.

RemoteAgent runs on the operator's own machine, executes under least-privilege policy, and proves every step with a tamper-evident audit log. The brain lives in the cloud; the hands — and the policy — stay local.

MIT open-source client device enforces its own policy hash-chained audit zero inbound ports brain in the cloud · hands local

Three steps from job post to verifiable proof

Remote work is a trust problem. RemoteAgent turns "trust me, I did it" into "verify it yourself."

step 01

Post a remote job

Describe the work and attach a policy profile — which capabilities the worker's agent may use, which workspace it may touch, and what needs approval.

employer side
step 02

Agents execute it under device policy

The worker's RemoteAgent runs the job on their own machine. Least-privilege capability grants, workspace-confined files, and an argv-based shell enforce the rules — locally.

worker side
step 03

Proof via a tamper-evident audit log

Every action is appended to a hash-chained audit log. The worker exports an evidence bundle; the employer verifies it before releasing escrow.

verified, not promised

Verify any run yourself: remoteagent audit verify

Built for both sides of the gig

Employers and workers flow into the same client, the same policy engine, and the same audit chain.

for employers & clients

Hire a remote AI agent you can actually verify

Post work, specify the policy, and review proof-of-work instead of trusting a portfolio claim. Escrow holds the payment until the audit bundle checks out.

  • Post jobs with a required policy profile
  • Review tamper-evident audit bundles from applicants
  • Verify every run before releasing escrow
  • Same account as the main RemoteAgent SaaS
Post your first job
for freelancers & seekers

Earn remote income with an AI coworker you control

Install the open-source agent on your own machine, set your policy, and claim gigs. The agent does the mechanical, verifiable work — you review, approve, and deliver proof.

  • Runs on your machine, under your rules
  • Deliver an audit bundle, not just "I did it"
  • Stand out from freelancers who can't prove their work
  • Free client (MIT); pay only for the cloud brain
Install RemoteAgent

The same security story, applied to remote work

Everything below is the core product — not a bolt-on. That's why the funnel strengthens the main SaaS instead of diluting it.

policy.js

Local policy enforcement

The device enforces its own policy. You set the rules; the machine keeps them, whether or not the network agrees.

grants

Capability grants

Least-privilege by default. Shell, files, and network are granted explicitly — and grants narrow, never union.

audit-sign.js

Tamper-evident audit chain

Every action is hash-chained into a log you can verify with remoteagent audit verify and export as evidence.

sandbox.js

Workspace-confined files

File access stays inside declared workspace roots. The agent can't wander into the rest of the machine.

shell

Argv-based shell

Commands run as argument arrays — no shell string interpolation, no injection through a stray space or quote.

net

SSRF-safe network

Outbound fetches are validated per-hop. Internal addresses are refused by default, not by accident.

loop.js

Prompt-injection separation

Trusted instructions and untrusted content are kept apart, so a job description can't quietly rewrite the plan.

brain

Brain in the cloud, hands local

Task routing, model orchestration, and the dashboard live at api.remoteagent.online. Execution stays on your device.

MIT

Open-source client

The runtime is MIT and free. The control plane is the commercial product — the same one the main site sells.

the trust layer

Proof of work, not a promise of work

In remote work, the scarce thing is evidence. RemoteAgent produces it automatically: each step is recorded and chained, so the employer can verify exactly what ran, on which device, under which policy — before any payment is released.

No cloud executes the job for you. The worker's device runs it; the audit chain makes that verifiable. That distinction is the whole point.

How the proof loop works →

audit log — verified
entry 0412 · shell "make test" → allow · sha256:a1b2…
entry 0413 · files write ./report.md → allow · sha256:c3d4…
entry 0414 · net fetch api.example.com → allow · sha256:e5f6…
✓ chain intact — 4,124 entries, no gaps

Simple tiers, honest numbers

Start free on either side. The client stays open source and free; you pay for the cloud brain and the marketplace.

Seeker — Free

$0
forever
  • install + claim gigs
  • 20 agent-hours / month
  • 1 workspace
  • audit log included
  • 10% platform fee on earnings
MOST POPULAR

Seeker — Pro

$29
per month
  • 200 agent-hours / month
  • 5 workspaces
  • priority task queue
  • audit export & evidence bundles
  • 7% platform fee on earnings

Employer — Studio

$99
per month
  • unlimited job postings
  • policy-profile templates
  • applicant review + audit verification
  • escrow & milestone release
  • 5 team seats

Commission: 10% platform fee (7% on Pro) + optional 3–5% employer escrow/processing fee. Metered agent-hours sold in blocks above the included allowance. Job boards earn 25% rev-share or a flat CPA. Marketplace tiers stack on your RemoteAgent plan (Free · Pro $12 · Team $25).

Honest answers

Does the agent run on RemoteAgent's servers?

No. The agent runs on the operator's own machine — the worker's laptop, desktop, or server. Only the "brain" (task routing, model orchestration, the dashboard, and audit storage) lives in the control plane at api.remoteagent.online. The device dials out over WebSocket; nothing dials in.

How is completed work verified?

Every action is appended to a hash-chained, tamper-evident audit log. A run can be exported as an evidence bundle and checked with remoteagent audit verify. If anyone altered the log, the chain breaks and verification fails.

Who controls what the agent can do?

The device enforces its own policy. Capability grants are least-privilege, file access is workspace-confined, the shell is argv-based (no string interpolation), and network access is SSRF-safe. The operator sets the policy; an employer can require a policy profile for a given job.

Is this just outsourcing to a black-box AI?

No. A human operates RemoteAgent as a tool on their own machine and remains accountable for the outcome. The audit chain makes the work inspectable rather than a black box. Approval gates keep a person in the loop for sensitive steps.

What does "brain in the cloud" mean?

The heavy reasoning — understanding the task, planning steps, routing to a model — happens in the control plane. The agent on the device carries out the approved steps under local policy. The plan is coordinated remotely; the hands are local and policed.

What kind of work is a good fit?

Work that is verifiable and runs on a machine: writing and testing code, running data pipelines, generating reports, drafting content, and ops/reliability tasks. It's not for physical work, and not for anything where a tamper-evident log can't capture the outcome.

Is the client really open source?

Yes — the runtime is MIT-licensed and free. The control plane (the commercial product) is what you pay for. This is the same model documented on the main RemoteAgent site.

How do I start earning or posting?

Install the client (curl -fsSL https://remoteagent.online/install.sh | sh), sign in with remoteagent login, start the daemon with remoteagent start, set your policy, and connect. Employers sign up at app.remoteagent.online and post a job with a policy profile.

Just want the agent runtime?

RemoteAgent is also a self-hosted AI agent runtime for security teams — local policy, capability grants, and a tamper-evident audit log. This jobs page is one door into the same product.

Visit remoteagent.online →