v3.12 — OpenClaw · Claude Code · Codex · Gemini · Ollama

Your own AI workstation.
Free. Open source.

A complete browser-based AI development environment you install on any VPS. Agent chat, sandboxed code execution, remote desktop, project management — connect your own AI providers and own your entire stack.

One-command install
$ curl -fsSL https://bridgesllm.ai/install.sh | sudo bash

Ubuntu 22.04/24.04 or Debian 12+. Takes 2–5 minutes. Disconnected? Run it again — it resumes.

https://your-vps.example.com
Why a VPS?

You don't need expensive hardware to work with AI.

A $20/mo VPS with flat-rate AI subscriptions costs a fraction of dedicated hardware + pay-per-token API keys. The portal is free — here's what the total setup looks like.

Best-value VPS + BridgesLLM Portal

VPS (e.g. Hetzner, DigitalOcean)$20–40/mo
Portal softwareFree
Claude (OAuth subscription)~$20/mo
Codex (OAuth subscription)~$20/mo
Gemini (OAuth subscription)~$20/mo
Hardware upfront$0
12-month total
~$960–$1,680
~$80–140/mo

Mac Mini M4 + API Keys

Mac Mini M4 (16GB)$800 upfront
Electricity (~150W average)~$13/mo
Claude API (heavy use)$50–200/mo
OpenAI API (heavy use)$50–150/mo
Amortized hardware cost~$67/mo
12-month total
$2,600–$6,200+
$217–517/mo

LIVE Gaming PC + API Keys

Mid-range gaming PC$1,200 upfront
Electricity (~400W average)~$35/mo
Claude API (heavy use)$50–200/mo
OpenAI API (heavy use)$50–150/mo
Amortized hardware cost~$100/mo
12-month total
$3,420–$7,620+
$285–635/mo

Cloud IDEs (Codespaces etc.)

GitHub Codespaces (4-core)~$0.36/hr
8h/day, 20 days/mo~$58/mo
No persistent environment
Limited AI agent support
12-month total
$696+ (no local agents)
$58+/mo

* API cost estimates based on moderate-to-heavy developer usage. OAuth flat-rate subscriptions cap your monthly cost regardless of usage volume.

Feature comparison

What you actually get.

Capability BridgesLLM Portal Mac Mini + APIs Gaming PC + APIs Cloud IDEs
Access from any browser Built-in~ VNC/RDP required~ VNC/RDP required Yes
Flat-rate AI model costs OAuth subs Pay-per-token Pay-per-token Pay-per-token
Claude / Codex / Gemini 6+ providers~ DIY setup~ DIY setup~ Limited
OpenClaw agent framework Built-in Self-managed Self-managed No
Sandboxed code execution Isolated per-project~ Manual setup~ Manual setup Yes
Remote desktop (browser) NoVNC built-in Extra software Extra software No
Project management + AI Included Not included Not included No
Self-hosted email server Included No No No
Self-updating dashboard Auto-updates Manual Manual Managed
Setup wizard (no CLI needed) Browser-based No No Yes
Works on $20/mo hardware Yes $800+ upfront $1,200+ upfront~ Usage-based
Your data on your server Always Local Local Cloud-hosted
Everything included

Your full AI dev stack.
One install.

Every tool you need to vibe code, run agents, and ship projects — without paying for or managing them individually.

Built on OpenClaw

Every major model. One agent framework.

BridgesLLM Portal runs on OpenClaw — the open-source agent framework that connects to every major AI provider via OAuth. Flat-rate access, no token counting, no surprise bills.

OpenClaw logo OpenClaw (agent framework)
Claude Code logo Claude Code (Anthropic)
Codex logo Codex (OpenAI)
Gemini logo Gemini (Google)
Ollama logo Ollama (local models)

OpenClaw, Claude, Codex, Gemini, and Ollama names and logos are trademarks of their respective owners and are shown for identification only.

How much are you saving?

All of this is free. Here's what the full setup costs.

BridgesLLM Portal is free and open source. You just need a VPS and your AI subscriptions. Compare that to buying hardware and paying per-token API rates.

Best-value VPS + BridgesLLM Portal

VPS (Hetzner, DO, Vultr, etc.)$20–40/mo
BridgesLLM PortalFree
Claude (OAuth sub)~$20/mo
Codex (OAuth sub)~$20/mo
Gemini (OAuth sub)~$20/mo
Hardware upfront$0
12-month total
~$960–$1,680
~$80–140/mo

Mac Mini M4 + API Keys

Mac Mini M4 (16GB)$800 upfront
Electricity~$13/mo
Claude API (heavy use)$50–200/mo
OpenAI API (heavy use)$50–150/mo
Amortized hardware~$67/mo
12-month total
$2,600–$6,200+
$217–517/mo

LIVE Gaming PC + API Keys

Mid-range build$1,200 upfront
Electricity~$35/mo
Claude API (heavy use)$50–200/mo
OpenAI API (heavy use)$50–150/mo
Amortized hardware~$100/mo
12-month total
$3,420–$7,620+
$285–635/mo

Cloud IDEs

GitHub Codespaces (4-core)~$0.36/hr
8h/day, 20 days/mo~$58/mo
No persistent environment
Limited AI agent support
12-month total
$696+ (no local agents)
$58+/mo

* OAuth flat-rate subscriptions mean predictable costs regardless of usage. Pay-per-token API pricing can spike unpredictably with heavy AI use.

Setup in minutes

From zero to AI workstation
in under 10 minutes.

1

Get a VPS

Hetzner, DigitalOcean, Vultr, Linode — any Ubuntu 22+ server for $5–40/mo. 2GB RAM minimum.

2

Run the command

Paste one curl command. Installation takes 2–5 minutes. It prints a setup URL when done.

3

Open the wizard

Domain, SSL, accounts — all configured in your browser. No SSH config files to edit.

4

Connect your models

Click OAuth "Connect" for Claude, Codex, or Gemini. Done. Start chatting and building immediately.

System requirements

Works on basically anything.

If you can SSH into it, you can run BridgesLLM Portal on it.

Ubuntu 22.04+ or Debian 12+
2GB RAM minimum (4GB recommended)
10GB free disk space
Root or sudo access
Ports 80 and 443 open
Any modern VPS provider

Your AI workstation is
one command away.

Free to install. Free to run. Pay only for the VPS and the model subscriptions you want.

Install command
$ curl -fsSL https://bridgesllm.ai/install.sh | sudo bash
Privacy Policy Terms of Use