Local-first · No token bills · Your models 1 IDEs online now

The coding agent that
runs on your hardware

An early-access agentic IDE that plans, edits files, runs tests, builds and previews real projects — and generates images and video from a chat prompt. Powered by open models on your hardware, with our own brutus-brain built in. Review agent changes before trusting them.

Windows early-access beta · No account needed for local mode · Ollama and a separate model download required
Install Ollama, download a model such as qwen3:4b, then open BrutusAI and select your project folder. Model downloads require several GB; speed depends on your hardware.
Download SHA-256 checksum · Start with a disposable test project and keep backups.
Windows may flag an unsigned or unfamiliar application. Verify the source and checksum before deciding whether to run it.
Sign in with Discord to join the community — free, no key or card required.
BrutusAI
BRUTUSAI

▸ src
▸ tests
app.py
index.html
README.md
import flask

app = flask.Flask(__name__)

@app.route("/")
def home():
  return "Built by BrutusAI"
Build me a portfolio site and preview it
write_file → index.html
start_server → :8910
preview → http://localhost:8910 ✓
Done — your site is live in the preview pane.

This is the real thing, running now

Actual screenshot of the build you can download — agent panel, file explorer, PowerShell terminal and live preview, all in one native window.

BrutusAI IDE — real screenshot

▶ Watch it work — 5s real capture

LocalOllama inference — performance depends on model and hardware
Choiceconfigure a model that fits your available RAM and VRAM
Optional cloudyour provider account, credentials and usage limits apply
Betaunder active testing — issues and incomplete tasks are possible
£0required to run — local Ollama models are free

A real agent, not a chatbot

BrutusAI doesn't just talk — it plans, writes files, runs tests, spins up servers and shows you the result live.

🤖

Autonomous agent loop

Plans tasks, calls tools, verifies its own output and keeps going until the job is done.

👁

Sees what it builds

Starts dev servers, previews your site in-app — then visits it with real browser automation to verify what it built.

🧠

Free cloud brains built in

Use local Ollama models offline, or configure your own OpenAI-compatible provider credentials. Cloud availability, free quotas and charges depend on the provider; Discord sign-in does not supply provider credentials.

🎨

Media studio built in

Generates images (SDXL-Lightning) and video (local text-to-video) straight from a chat prompt — fully offline, no API keys, no per-image fees.

🧬

brutus-brain inside

Our own fine-tuned model, trained in-house on real agent tasks — 250 chats free on every install. It remembers techniques it learns and stops asking twice.

💓

An honest persona

Ask how it feels — it reads live GPU, RAM and uptime telemetry and answers from real numbers. When the hardware's struggling, it tells you.

🔊

Premium neural voice

Microsoft neural TTS — natural spoken replies, five voices, completely free and keyless.

🛡

Self-healing autopilot

Watches its own services, restarts what's down, re-verifies builds, and keeps the public site live — unattended.

🌐

Web-aware

Searches docs, fetches pages and installs frameworks when the task needs them.

🔒

Permission modes

Seven modes — normal, smart, accept-edits, bypass, autonomous, plus plan & ask for read-only analysis.

⏪

Checkpoints & sessions

Every agent edit is restorable. Sessions persist — pick up right where you left off.

Simple pricing

Run it free on your own hardware, or let us host the brain.

Free

£0 forever
  • Full BrutusAI IDE — every feature
  • Runs on your own Ollama models
  • 250 free chats on brutus-brain
  • Unlimited usage on your hardware
  • All agent modes & permissions
  • Discord community + free Member role
  • No key, no card, no sign-up walls
Download free Join Discord free

Pro Weekly

£1.99 / week
  • Everything in Free
  • Unlimited brutus-brain chats
  • Connect to our hosted model server
  • No local GPU needed — works on any laptop
  • Faster responses & bigger context
  • Customer ⭐ role on Discord
  • Launch price — locked forever
BEST VALUE · LAUNCH PRICE

Pro Monthly

£3.99 / month
  • Everything in Free
  • Unlimited brutus-brain chats
  • Connect to our hosted model server
  • No local GPU needed — works on any laptop
  • Faster responses & bigger context
  • Customer ⭐ role on Discord
  • Priority support
  • ~92p/week — save 54% vs weekly

Hosted plans are planned, not currently available for purchase. Prices shown are provisional. Billing setup and independent tenant isolation verification are required before launch. The local beta is available now.

FAQ

What do I need for free mode?

A Windows PC, Ollama, and one model pull (ollama pull qwen2.5-coder:7b). After that BrutusAI runs fully offline — no API keys, no token bills.

What does Pro actually give me?

An access key to our hosted model server. Your laptop stops running the model — everything offloads to our infrastructure, so it's faster and works on machines with no GPU.

What is brutus-brain?

Our own fine-tuned model, trained in-house on real agent tasks — tool calls, coding, browser use, media generation. Your first 250 chats on it are free; Pro removes the cap. Every other model stays free and unmetered forever.

Is it actually like Devin?

Same workflow shape — agent plans, edits files, runs commands, previews results — but powered by open models you own. Honest take: a local 7B model won't match Devin's proprietary model on huge tasks, but for everyday builds and edits it delivers, and it costs nothing to run.

Can I host it for my own team?

Yes — run the server on any machine, hand out access keys to your team. Keys are per-user, revocable, and the free tier is rate-limited out of the box.

Why is Pro so cheap?

Deliberate. We're building the community first — the IDE is free forever, Discord membership is free, and launch pricing is set low enough that upgrading is a no-brainer. Early members keep their price locked forever, even as it goes up for everyone else.