self-hosted · continuously learning

A market model that keeps learning.

flint is a self-hosted neural network that reads live market data, forecasts the next hour for a basket of stocks, and shows its reasoning as it goes. A local model even writes the daily brief. It runs on your machine and your keys stay with you.

Get started View on GitHub

Python · PyTorch · FastAPI · a no-build dashboard · optional local LLM via Ollama

The flint dashboard: candlestick cards with forecasts, a whole-market panel, and live ticks

the live dashboard — candles, MACD, a forecast fan, and cards that reorder by urgency

What it does

A forecasting model, a trading dashboard, and a window into the model's head, in one thing you run yourself.

🧠

Always learning

It trains online as its forecasts mature, and its calibration keeps it honest. When it has no real edge it holds, instead of trading noise.

📈

Live charts

Every stock gets a candlestick chart with MACD and a forecast fan. Cards rank by urgency and reorder in real time, and any chart flips between 5 and 1 minute bars.

🔦

See it think

A control panel streams the model's consciousness across eight consoles, and a Console tab tails everything at once: the feed, the features, the forecasts, the policy, the training.

📝

On-device brief

Small models summarize the tape, the macro backdrop, positioning and the smart money. A larger local model turns those notes into a plain newspaper column. It all runs through Ollama, so nothing leaves the machine.

🏛️

Investor council

A panel of well-known investors, built from their real 13F filings and documented style, nudges the model. Burry, Buffett, Ackman, Icahn and others.

🛰️

Whole-market radar

Breadth, sector rotation, volatility and a large movers watchlist give you and the model the full picture. Penny and small-cap movers included.

🔒

Local and private

Everything runs on your machine. API keys sit in gitignored files and only ever talk to their own provider.

⚙️

Fits your machine

A first-run benchmark sizes the network to your hardware and uses the GPU when there is one, so it runs on a laptop or a workstation.

How it works

It behaves less like a backtest and more like a trader who shows up every morning and keeps score.

Warm up

flint pulls intraday history, benchmarks your machine, and trains on the recent session before it goes live.

Stream and forecast

Real trades drive the charts. Each bar the model forecasts the next hour and turns it into a buy, sell or hold with a reason in plain English.

Learn as it goes

An hour later every forecast is scored and the model recalibrates. You judge it on live accuracy over hours, not on how well it fit the past.

A single stock card with candlesticks, MACD, forecast fan and a plain-English rationale — Each card shows the forecast, the band, and why the call is a buy, sell or hold.

The Console tab: a terminal-style stream of everything the model is doing — The Console tab tails every channel the model runs through, live.

Run it

You need Python 3.12 and uv. For the written brief, install Ollama and pull a model.

# clone and install
git clone git@github.com:thingg-co/flint.git
cd flint
uv sync

# run it, then open http://localhost:8000
uv run flint

# optional: a local model for the daily brief
ollama pull qwen3.5          # or any chat model you like

It works out of the box on free, no-key data sources. On first launch a short walkthrough lets you add API keys for better feeds, and you can skip any of them. Everything, including the LLM brief, runs locally.