Train RL agents in your browser

IgnitionAI is the ML-Agents of the JavaScript creative ecosystem. Describe your game world, call env.train(), and deploy anywhere via ONNX. No Python, no server, no GPU cluster.

$npm install @ignitionai/core @ignitionai/backend-tfjs @ignitionai/environments
Quick Start

Train your first agent in 7 lines

No neural network code. No hyperparameter tuning. No config files. Describe your world, call train(), and the framework does the rest.

cartpole.ts
import { IgnitionEnvTFJS } from '@ignitionai/backend-tfjs';
import { CartPoleEnv } from '@ignitionai/environments';

const cartpole = new CartPoleEnv();
const env = new IgnitionEnvTFJS(cartpole);

env.train('dqn');      // Zero config. It just works.
// env.infer();        // Switch to inference after training.
// env.setSpeed(50);   // Turbo training (50x faster).

That's it. The agent learns. The pole stays up.

Built for creative JS devs

Reinforcement learning that fits your stack

Describe your world in a class, call env.train(), and watch your agent learn in real time. No Python, no server, no GPU cluster.

Everything you need to ship RL.

Three algorithms, auto-configuration, ONNX export, HuggingFace storage, and five working demos. All TypeScript, all open source.

Train → ONNX → deploy anywhere

Train in the browser with TensorFlow.js, then export to ONNX and deploy in Unity (Sentis), Unreal (NNE), Python, C++, or edge devices. One pipeline from prototype to production.

BrowserTF.jsONNX.onnxUnitySentisUnrealNNEPythonORTEdge / C++Mobile · WASMtrainexport

Three algorithms, one API

DQN, PPO, and tabular Q-Learning. Switch with one word: env.train('ppo'). Override hyperparameters only when you need fine control.

DQNValue-basedepisodesPPOPolicy gradientepisodesQ-TableTabular

R3F-first

Pair it with your Three.js scene — training loop runs independently of the render loop.

R3F

Auto-configuration

Input size deduced from observe(), action size from actions.length. You never touch network code.

WebGPU acceleration

TensorFlow.js auto-selects WebGPU → WebGL → WASM → CPU. No CUDA, no install.

Turbo training

env.setSpeed(50) — 50× faster convergence. Drop back to 1× to watch the agent play.

HuggingFace storage

Save and load trained models from HF Hub with one line. Share weights like a dataset.

Strict TypeScript

No any, Zod-validated configs, 184+ tests, CI/CD. Production-ready from day one.

Five working demos

GridWorld, CartPole, MountainCar, CartPole 3D, and Car Circuit. Clone, run, learn.

Interactive Playground

Train an agent in your browser

Pick an algorithm, hit Train, and watch the reward climb in real time. This is a simulation — open a live demo below to run real RL.

1x
Ready
Click Train to start
Episode 0
Episode 50
Reward 200
Recent updates

What's new

IgnitionAI ships fast. Here's the latest release — everything else lives on the full changelog.

v0.2.0-devLanding, Docs, and Physics DemoApril 15, 2026
  • Landing & sitePublic site live at [ignitionai.dev](https://ignitionai.dev)
  • Landing & siteSingle Next.js deployment serving the landing, the docs, and the demos
  • Landing & siteBrand: animated flame GIF logo, indigo palette, 3 custom inline SVG feature diagrams (ONNX pipeline, algorithm cards, R3F integration)
  • Landing & siteFlame favicon across every page (`app/icon.svg`) and every demo
  • Documentation20-page Nextra documentation site under `/docs`
Open source · MIT licensed

Ready to train your first agent?

One install command, one TrainingEnv class, one call to env.train(). Your agent learns in your browser, then deploys anywhere via ONNX.