A VISIONARY SPARKS PRODUCT · OPEN SOURCE

Symposium — your own AI lab, on your own machine.

Run open-source AI models locally, share them across your network, race two models head-to-head, and learn machine learning by training a small model yourself. One app — Windows, Linux and Android. No cloud bill.

⬇ Download for Windows ⬇ Download for Linux ⬇ Download for Android Source on GitHub

Free · Apache-2.0 open source · fully offline — models run on your hardware, nothing leaves your network

Everything happens by clicking — not in a terminal

Local AI is powerful but trapped behind command lines. Symposium puts installing, running, sharing, comparing and even training models behind buttons.

💬

Chat with local models

One-click model download and streaming chat with open-source LLMs running on your own PC — with live tokens-per-second.

📡

Host mode & discovery

Flip one toggle and your PC serves its models to your friends' phones and laptops on the same network. They find it automatically.

⚔️

Arena mode

Two panes, any two models on the network. Fire one prompt at both, watch them race, and vote on the winner.

🧪

Parameter lab & personas

Play with temperature, top-p and system prompts in a live edit-and-retest loop. Share personas as small JSON files.

🎓

Training studio

Train a tiny GPT on your own machine and watch the loss curve fall in real time — then chat with your half-trained model. The best way to feel how ML works.

📖

The companion book

LEARN.md teaches everything from scratch — tokens, streaming, network discovery, loss curves — one chapter per feature you can see running.

Why a company built on ₹0-cost AI made this

Classmate AI teaches you concepts with Astra. Symposium is where you get your hands dirty: if you're learning machine learning, the moment it clicks is when a model you trained yourself says its first (terrible) sentence. Everything runs on your hardware — no API keys required, no cloud bill, nothing to top up. That's the same cost-first philosophy the rest of Visionary Sparks runs on.

Where it stands

✅ Working today

  • · Streaming chat + in-app model downloads (Ollama engine)
  • · Host mode, LAN discovery, pairing codes
  • · Split-screen arena with duel mode & voting
  • · Parameter lab, personas, conversation history
  • · Model-library browser, image & PDF attachments, themes
  • · Training service: tiny GPT with live metrics (backend)

🔭 Coming next

  • · In-app training studio UI
  • · Symposium Link — join a friend's model across the internet with a short code, no port forwarding, no code. Town A trains, town B tests.
  • · Bundled engine — zero external installs
  • · Signed installers & Play Store listing

Openly built, early and honest: today devices find each other on the same Wi-Fi automatically; across the internet you can already join by IP if the host forwards a port. The one-code version is next.

Get Symposium

🖥️ Windows

  1. Download the zip and extract it anywhere.
  2. Install Ollama once — Symposium drives it for you, no terminal ever.
  3. Run symposium.exe and download a model from inside the app.
⬇ Download for Windows (.zip)

📱 Android

  1. Download the APK and open it (allow "install from this source" when asked).
  2. Your phone finds any PC on the same Wi-Fi running Symposium in host mode — chat with the big models from your pocket.
⬇ Download for Android (.apk)

Unsigned early-access build — Play Store listing is on the roadmap.

🐧 Linux

  1. Download the tarball and extract: tar -xzf Symposium-linux.tar.gz.
  2. Install Ollama once (e.g. pacman -S ollama on Arch); Symposium drives it.
  3. Run ./symposium (needs GTK3: pacman -S gtk3).
⬇ Download for Linux (.tar.gz)

Stuck? Email us — we answer.