agentos.guide › blog
StarNet Reviews: My Verdict, The Quick Start, And Where It Fits In An Agent OS
StarNet reviews usually want one answer, and mine is that this free, open-source AI agent harness earns 3.5 out of 5.
StarNet runs your AI agents inside a pixel-art space station on your own computer, and it's the most fun office-style agent tool I've tested.
I don't think there's a massive amount of practical use cases yet, so I run it as a tab inside my Agent OS rather than as my main engine.
This page gives you my verdict and scores, the quick start, and how StarNet fits an Agent OS workflow.
If you want my team to look at how your business can get found in Google and AI search, book a free SEO strategy session with my team.
My StarNet review in one table
My overall verdict is 3.5 out of 5.
These scores are my own opinion from my own install of v0.13.1, not a lab benchmark.
| What I scored | My score | Why |
|---|---|---|
| Fun and design | 10/10 | It's the most enjoyable agent interface I've used. |
| First-run setup | 8/10 | The first agent takes one or two clicks, but my source install needed npm ci. |
| Brain and model choice | 8/10 | Subscriptions, API keys and local models all work. |
| Permissions and control | 9/10 | Web and file access are clear switches on each agent. |
| Crew and multi-agent | 9/10 | Recruit, deploy and summon turn one agent into a visible team. |
| Chat speed | 6/10 | There's a slight delay every time you send a message. |
| Practical business use | 5/10 | I don't think there's a massive amount of practical use cases yet. |
| Maturity | 6/10 | The README itself calls it an early release. |
| Value for money | 9/10 | The code is free, and you only pay for the brain you connect. |
| Overall | 3.5/5 | It's fun, polished and free, and it's not yet my main work tool. |
The short version is that StarNet is the most fun agent station I've tested, and it lives inside my Agent OS as a side tab rather than as my main engine.
What StarNet is
StarNet is a local-first desktop agent harness made by Andrew Sims, who publishes it on GitHub as androoAGI/starnet.
The repo calls it "a living pixel-art station where real AI agents do real work."
It's open source under the MIT License, and the repo has more than 1,500 GitHub stars.
The README says agents make real model calls, use real tools and create real costs, so nothing in the station is faked.
It also says the interface must never show a state the harness can't prove.
The latest release on 16 October 2026 is v0.13.5, and I tested v0.13.1.
If you've been searching "Startnet OS", it's the same tool, and my Startnet OS reviews guide explains the name.
StarNet quick start in six steps
This is the fastest route from nothing to a working agent.
| Step | What you do | What I saw |
|---|---|---|
| 1 | Download the desktop app for Windows or macOS, or clone the repo and run it from source. | My source install on a Mac needed npm ci first. |
| 2 | Open the local web app in your browser. | The README uses port 8787, and mine runs on port 8788. |
| 3 | Create an agent with a name, a look and a personality. | I saw warm, dry, composed and unhinged personalities. |
| 4 | Pick "ask for approval" or "full power". | I'd start on ask for approval. |
| 5 | Connect a brain and choose the model and reasoning level. | I signed in with Grok and picked Grok 4.6. |
| 6 | Wake the agent up and give it a direction. | Mine said, "I'm awake. Let's give the station a direction." |
The desktop builds live on the StarNet releases page.
Running from source needs Node.js 18 or newer and Git.
The README says the sidecar runs on Node core modules only, but my install still needed npm ci, so allow for that.
The README says Windows is the most-tested platform and macOS has less real-world coverage.
If you want my team to look at how AI agents and content can get your business found in Google and AI search, book a free SEO strategy session.
🔥 Want the exact StarNet setup I run inside my Agent OS?
Inside the AI Profit Boardroom you get the installable Agent OS, step-by-step video tutorials, four coaching calls a week and 3,400+ members building real automations.
Which brain to plug in
StarNet doesn't ship its own model, so the brain decides how capable your agents are.
In my video I explained that it can plug into a Claude Code subscription through the Claude CLI, Kimi and Grok.
The README adds an OpenRouter key and sign-ins for supported Anthropic, OpenAI and Google accounts, with keys kept in the OS keychain.
For a free route, the README shows Ollama with qwen3:8b as the example.
It warns local models are slower and rougher on long tasks, and an 8B model needs about 10 GB of graphics memory.
I chose Grok 4.6 over Grok 4.7, because I actually prefer Grok 4.6.
How StarNet fits your Agent OS
I embedded StarNet as a tab inside my own Agent OS, next to my other agents.
That's the setup I'd recommend, because it gives you the fun station without moving your real work into an early release.
| Agent OS job | Where StarNet helps | Where I use something else |
|---|---|---|
| Learning how a crew behaves | You can watch agents level up, take roles and stand together in the station. | StarNet is the most fun way I've found to see this, so I use it as it is. |
| Light daily helpers | The daily brief, widgets and app catalog cover small jobs. | I keep scheduled production work in the main Agent OS. |
| Real business pipelines | It can connect Gmail, Notion and GitHub. | I run SEO and publishing jobs through Hermes and Claude in the Agent OS. |
| Showing a team what agents are | The pixel-art station makes agents easy to explain. | I use the Agent OS for the real handover. |
My Agent OS is my own product, so weigh my recommendation with that in mind.
🔥 Want the exact StarNet setup I run inside my Agent OS?
Inside the AI Profit Boardroom you get the installable Agent OS, step-by-step video tutorials, four coaching calls a week and 3,400+ members building real automations.
Every part of the station I tested
The station view lets you zoom in and out, change the frame and go to a full zoom.
Everything you run lives in four docks, which you can click open, show all at once or drag around.
Agents level up the more you use them, which makes the whole thing feel like a Tamagotchi for an AI agent.
The agent detail panel shows the model, the personality, the instructions and purpose, access permissions and approval prompts.
You can change the personality any time, and you can allow or remove web and local file access.
The Brief, Growth, History and Memories tabs show what each agent is for, how it's grown, what it did and what it remembered.
Chat shows each agent's online status and level, and the left-hand list switches between idle and online agents.
You can manage projects and sessions from that list too.
My agent asked, "What made you want to set up an AI agent?", and I told it SEO and gave it aiprofitboardroom.com.
There's a slight delay when you send a message.
The plus button adds widgets such as connected apps, pinned widgets, an app chooser and a daily brief, and you choose what each one shows.
The app catalog, labelled "add an ability", includes Gmail, Notion and GitHub, and most apps sign in directly while some need an API key.
It also has real-world categories such as finding flights, sending physical letters, email and web search through Firecrawl.
The skill market has standard originals like ad copy testing and calendar scheduling, with some built in, some installed later and community updates.
The skill library holds frameworks such as a decision framework for hard technical problems, making a plan, humanising content and handling a hard conversation, and you can switch each one on or off.
Crew and Recruit give you roles like strategist, chief of staff, researcher and marketer, each with a name and appearance.
Deploy overwrites an existing agent's setup with a role, and Summon adds a new agent next to yours.
Tasks, quests, a work list, builds and a Systems menu all live in one system.
If you'd like my team to map out where agents fit your marketing, grab a free one-to-one strategy session and we'll look at your site, your competitors and the keywords you're closest to winning.
StarNet pros and cons
- The biggest pro is that it's the smoothest office-style agent tool I've tested.
- Another pro is that per-agent permissions are clear and easy to change.
- Another pro is that the crew system makes a real team visible.
- The biggest con is that I don't see a massive amount of practical use cases yet.
- Another con is the slight delay on chat messages.
- Another con is that my source install needed an extra
npm cistep.
What other people asked
Several viewers on my video asked for more tutorials.
One viewer was frustrated that StarNet couldn't be used with Hermes Agent.
The README doesn't list Hermes Agent as a brain, but it says StarNet can import an existing Hermes or OpenClaw agent's persona, instructions, memory and model.
It says API keys don't transfer, so you re-enter them.
StarNet felt like a much more fun version of Paperclip to me, and it reminded me of the first time I tested Hermes Agent.
What v0.13.5 changes
I haven't re-tested since v0.13.1, so these points come from the official release notes.
- The notes say your lead agent can add crew to a conversation when you ask it to.
- They say delegated work gets its own threads and a live card showing who is doing what.
- They add a NEEDS YOU list that gathers every approval and question waiting on you.
- They say conveyor lines are now built with drag-and-drop, and finished jobs can be sent on to another line.
- They say Claude Code runs are faster and cheaper.
The notes also tell you to save a station backup first if you might ever roll back to 0.13.3 or older.
StarNet alternatives, ranked
This is my own ranking, and my own product is first, so weigh that.
| Rank | Name | Best for |
|---|---|---|
| 1 | Agent OS (my own, inside the AI Profit Boardroom) | Running Hermes, Claude and other agents from one dashboard with shared memory. |
| 2 | StarNet | A fun, gamified station where you watch a crew work. |
| 3 | Herald OS | A free desktop-style interface built around Hermes Agent. |
| 4 | Hermes3D | A 3D or 2D virtual office for agents you host yourself. |
My Herald OS guide and my Hermes3D guide cover the two free alternatives.
Also On Our Network
FAQ
Is StarNet any good?
Julian rates StarNet 3.5 out of 5. It is the smoothest and most fun office-style agent tool he has tested, with clear permissions and a strong crew system, but it is an early release with a slight chat delay and, in his view, not a massive amount of practical use cases yet.
Is StarNet free?
Yes. StarNet is free and open source under the MIT License. Paid models you connect still cost money, while a local model through Ollama costs nothing per message.
How do I install StarNet?
Download the desktop app for Windows or macOS from the StarNet releases page, or clone github.com/androoAGI/starnet and run it from source with Node.js 18 or newer. Julian's source install needed npm ci before it would run.
Can I run StarNet inside an Agent OS?
Yes. Julian embedded StarNet as a tab inside his own Agent OS, which members get inside the AI Profit Boardroom, so he can use the station without moving his main work into it.
Does StarNet work with Hermes Agent?
Hermes Agent is not listed as a brain in the README. The README says StarNet can import an existing Hermes or OpenClaw agent's persona, instructions, memory and model, and you re-enter the API keys.
Is Startnet OS the same as StarNet?
Yes. Startnet OS is a common misspelling of StarNet, and Julian's own video title calls it the StarNet Agent OS.
Final word on StarNet reviews
Install StarNet, create one agent on "ask for approval", and enjoy the most fun agent station I've tested.
Keep your money-making jobs on a proven system while StarNet matures.
If you want a clear plan for getting your content found in Google and AI search, book your free strategy session here.
If you want the Agent OS with StarNet already built in as a tab, it lives inside the AI Profit Boardroom, with 3,400+ members and four coaching calls a week.
That's my honest verdict across these StarNet reviews.
About Julian
I'm Julian Goldie, an AI entrepreneur, SEO expert and the founder of the AI Profit Boardroom, which has 3,400+ members.
I help business owners scale with AI agents, automation and SEO.
My YouTube channel has 400,000+ subscribers, and I run Goldie Agency, a seven-figure SEO agency.
Related guides on agentos.guide
→ StarNet AI Agent In Your Agent OS
→ StarNet GitHub: Install And Updates
→ The Best UI For Hermes Agent
Get the whole Agent OS
The installable system behind every guide on this site — dashboard, agents, memory and pipelines — updated as new tools land, with 3,400+ members and four coaching calls a week.
Join the AI Profit Boardroom →📺 Video notes + links to the tools 👉
🎥 Learn how I make these videos 👉