ai-trains-ai
RL-training an AI agent to RL-train AI agents.
What is it?
What it is
> 🔓 **Everything is open sourced** including: the trained agent's weights (LoRA adapter on 🤗 HF), agent harness, task families, reward code, GPU orchestration, tinker RL training scripts, and retro write-ups of every pilot (including the failures). Jump to Getting started ↓
Why it exists
RL-training an AI agent to RL-train AI agents.
Who should use it
Teams building with Python who want an open-source, self-hosted option.
Who should avoid it
Teams that need a fully managed SaaS with enterprise SLAs out of the box.
How it works
A quick walkthrough in plain English
How ai-trains-ai works
Step 1 of 3
You interact with it
Open ai-trains-ai, send a request, or connect it to your stack.
Features
Advantages
- Open source (MIT)
- Active Python ecosystem
- Self-hosted deployment options
Disadvantages
- Requires operational ownership for self-hosted setups
- Community support varies by project maturity
Installation
native
# .env at repo root with OPENROUTER_API_KEY=... (and TINKER_API_KEY for outer RL) uv sync uv run pytest # fully offline: no network, no keys uv run at-episode --task examples/tasks/calc_chain_v1_fast.json --model qwen3.6-27b # run one episode with a frontier agent
FAQ
What is ai-trains-ai?
ai-trains-ai is an open-source project licensed under MIT.
What language is ai-trains-ai built with?
Primary language: Python.
Is it free to use?
Yes. Licensed under MIT. Check the license for commercial use.
Featured in Videos
YouTube tutorials and walkthroughs for ai-trains-ai
Alternatives
Similar projects ranked by category, topics, and text overlap.
