synth-ai 0.2.6.dev2

RL as a service SDK - Core AI functionality and tracing

Synth-AI

Docs: Synth‑AI Documentation

Fast and effective reinforcement learning for agents, via an API

Highlights

• Easily scale gpu topologies - train on 3 a10gs or 8 H100s (multi-node available upon request)
• Requires only a thin fastapi wrapper to integrate with existing agent software.
• Supports the best OSS models like Qwen3. (gpt-oss available upon request, GA soon)
• Own your trained models

Getting Started

synth-ai comes with a built-in RL example tailored for training Qwen/Qwen3-0.6B to succeed at Math.

Please create an account at Synth and Modal for the Math hello‑world test run. Then run:

uvx synth-ai rl_demo check
uvx synth-ai rl_demo deploy
uvx synth-ai rl_demo configure
uvx synth-ai rl_demo run

To walk through kicking off your first RL run, see the Synth‑AI Documentation.