Always-on connection
turborg holds your IRC connection around the clock so you never drop off. Close your client and stay joined, then pick up the full backlog the moment you return.
always-on AI bouncer · open models · honest pricing
The always-on AI bouncer
…or run it in your terminal:
The always-on AI bouncer
for IRC.
turborg keeps you connected around the clock and adds an AI to your channels: polish messages, summarize what you missed, run agents on command. Use the web chat or your own IRC client. Free to start, no card.
curl -fsSL https://turborg.com/install.sh | sh borg, the same AI as a coding
agent · about borg → turborg · IRC connector · AI Polish · channel summaries
A bouncer that never sleeps, with an AI in every channel.
We have run IRC infrastructure since 2009. turborg takes that battle-tested foundation and adds an AI layer no other bouncer offers, live across 17 networks today.
An AI that lives in your channels
Polish a message before you send it, summarize a channel you have been away from, or hand a task to an agent. All from inside the chat, on an AI budget you set.
A web chat that feels modern
Emoji, link previews, themes, mentions and mobile. Or attach HexChat, irssi or whatever client you already use through the built-in bouncer.
irc.libera.chatirc.oftc.netirc.dal.netirc.undernet.orgirc.efnet.nlssl.ircnet.ioirc.quakenet.orgirc.esper.netirc.hackint.orgirc.tilde.chatirc.alphachat.netirc.lizardirc.org
One agent, many connectors. Explore turborg →
People already run their networks on turborg.
I'm mainly using it as an IRC bouncer and I've been very satisfied. The server's been stable and the control panel is responsive and easy to use.
The one-click summary feature is a lifesaver :) I leave my channels open but never actually read them. Now I just click the button when I wake up and get the TL;DR. UI looks nice too, dark mode is awesome! 5 stars.
Finally an IRC client that doesn't look like it was built in 1995 but also doesn't lag like Discord. It's good.
Open models
The AI runs on models we fine-tune ourselves.
We build on the best open-weight models (DeepSeek, Gemma), fine-tune them on our own data, quantize them to run lean and wrap them in an agent harness. We do not pretrain from scratch, and we are honest about it. The payoff is yours: AI that is fast, cheap enough to include in every plan, and not locked to a single vendor.
Inside our AI research →- open weights
- fine-tune
- own dataset
- quantize
- distill
- agent harness
- evals
- fast inference
Also: borg, in your terminal
The same AI as a coding agent in your shell.
turborg lives in your channels. borg is the same AI pointed at your repo: a terminal-native coding agent that reads your codebase, writes the change across as many files as it takes, runs your tests and checks its own work. One account covers both.
Meet borg → $ borg "fix the failing checkout test" · bash go test ./internal/checkout/... ✗· read_file internal/checkout/total.go ✓· edit_file internal/checkout/total.go ✓· bash go test ./internal/checkout/... ✓ ok internal/checkout 0.21s Fixed an off-by-one in the tax rounding. Test is green.
$ borg "add a /health endpoint that returns JSON status" · grep "func .*Router" ✓· write_file internal/api/health.go ✓· edit_file internal/api/router.go ✓· bash go build ./... ✓ Added GET /health returning {"status":"ok"} and wired it into the router.
$ borg "why does login take ~2s?" · grep "func Login" ✓· read_file internal/auth/login.go ✓· read_file internal/auth/hash.go ✓ The bcrypt cost is 14 (~1.6s per hash). Dropping to 12 gives ~0.2s and is still safe.
a real borg session · reads · edits · runs · verifies
Always-on plus an AI budget. Start free.
Each plan keeps your turborg always-on and sets a daily AI budget for polish, summaries and agents. One account covers turborg (always-on) and borg (terminal), on a plan you can read top to bottom.
Free
$ 0 /mo
Start freeStarter
$ 10 /mo
See planPro
$ 24 /mo
See planMax
$ 60 /mo
See planFull breakdown of tokens, limits and features on the pricing page →
New AI, on infrastructure we have run since 2009.
xShellz is not a weekend project. The shells, runtimes and networks under borg and turborg have been online for over fifteen years, and the whole thing is open source. The intelligence is new. The ground it stands on is not.
180k+ Developers and members
15+ Years online, since 2009
OSS Open source on GitHub
24/7 Always-on, never sleeps
Frequently asked questions
Can't find your answer? Ask support →
What is turborg?
turborg is an always-on AI bouncer for IRC. It holds your connection around the clock so you never miss a message, and puts an AI in your channels: message polish before you send, one-click summaries when you have been away, and agents on command. Drive it from a premium web chat or your own IRC client.
How is turborg different from a bouncer like ZNC?
A bouncer like ZNC holds your connection, and turborg does that too, with nothing for you to host or patch. The difference is the AI layer no other bouncer has: polish, summaries and skills inside your channels. You can self-host the open source core, or let us run the managed, always-on instance.
Which models does the AI run on?
Open-weight models (built on DeepSeek and Gemma) that we fine-tune, quantize and wrap in an agent harness ourselves. We do not pretrain from scratch and we are honest about that. The goal is AI that is fast, efficient and cheap enough to include in every plan.
Do I have to run a server?
No. xShellz runs the always-on, managed instance on infrastructure we have operated since 2009, so there is nothing to deploy or babysit. If you would rather self-host, the core is open source on GitHub and you can run it yourself.
Is it really free to start?
Yes. The free plan needs no card and includes a real AI budget so you can put turborg in an actual channel. When you outgrow it, Starter, Pro and Max raise the limits and keep your turborg always-on around the clock.
What is borg?
borg is the same AI as a coding agent in your terminal. You give it a task in plain language and it reads your codebase, makes the change across as many files as needed, runs your tests, and checks its own work. One account covers both turborg and borg. See the borg page for the full story.
Put an AI in your channels, free.
No card, no seat fee. Sign up and your always-on turborg is live in minutes.