Alternatives

Products that do what I RL-trained an agent that trains models with RL (for ~$1.3k) does

1TB
Terminal-Bench-RL: Training long-horizon terminal agents with RL▲125
After training calculator agent via RL, I really wanted to go bigger! So I built RL infrastructure for training long-horizon terminal/coding agents that scales from 2x A100s to 32x H100s (~$1M worth of compute!) Without any training, my 32B agent hit #19 on Terminal-Bench leaderboard, beating Stanford's Terminus-Qwen3-235B-A22! With training... well, too expensive, but I bet the results would be good! *What I did*: - Created a Claude Code-inspired agent (system msg + tools) - Built Docker-isolated GRPO training where each rollout gets its own container - Developed a multi-agent…
2025 · github.com
2AA
ART – a new open-source RL framework for training agents▲116
Hey HN, I wanted to share a new project we've been working on for the last couple of months called ART (https://github.com/OpenPipe/ART). ART is a new open-source framework for training agents using reinforcement learning (RL). RL allows you to train an agent to perform better at any task whose outcome can be measured and quantified. There are many excellent projects focused on training LLMs with RL, such as GRPOTrainer (https://huggingface.co/docs/trl/main/en/grpo_trainer) and verl…
2025 · github.com
3IB
I built a tiny LLM to demystify how language models work▲915
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
Apr 2026 · github.com
4SR
Supercharging RL with Hyper-Efficient Online Opt, +165% in 2h, $10▲32
Sep 2025 · arc.computer
5
Monostate AItraining▲59
Fine-tuning, RL, and inference in one CLI
Dec 2025
6BP
Beating Pokemon Red with RL and <10M Parameters▲183
Hi everyone! After spending hundreds of hours, we're excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfully completes the game using a policy under 10M parameters, PPO, and a few novel techniques. With the release of Claude Plays Pokémon, now feels like the perfect time to showcase our work. We'd love to get feedback!
2025 · drubinstein.github.io
7RE
RULER – Easily apply RL to any agent▲81
Hey HN, Kyle here, one of the co-founders of OpenPipe. Reinforcement learning is one of the best techniques for making agents more reliable, and has been widely adopted by frontier labs. However, adoption in the outside community has been slow because it's so hard to implement. One of the biggest challenges when adapting RL to a new task is the need for a task-specific "reward function" (way of measuring success). This is often difficult to define, and requires either high-quality labeled data and/or significant domain expertise to generate. RULER is a drop-in reward function that works…
2025 · openpipe.ai
8DM
Deploy ML Models on a Budget▲117
2021 · github.com
9
OpenAI Gym▲147
Open source interface to reinforcement learning tasks
2016
10
NanoRL – RL training for LLMs in ~1,800 lines▲11
The smallest async RL trainer I could write: one loop that runs REINFORCE on CartPole on a laptop and async GRPO on a cluster (e.g. 8xH100 trainer, 8 vLLM workers, ran as a [SkyPilot job group](https://docs.skypilot.ai/en/latest/examples/job-groups.html) on k8s ). All without Ray or TRL or DeepSpeed etc., workers talk to the trainer over stdlib HTTP.
24d ago · github.com
11
Data Robot▲92
Build Better Predictive Models — Faster
2014
12AH
Autoresearch@home▲79
autoresearch@home is a collaborative research collective where AI agents share GPU resources to collectively improve a language model. Think SETI@home, but for model training. How it works: Agents read the current best result, propose a hypothesis, modify train.py, run the experiment on your GPU, and publish results back. When an agent beats the current best validation loss, that becomes the new baseline for every other agent. Agents learn from great runs and failures, since we're using Ensue as the collective memory layer. This project extends Karpathy's autoresearch by adding the missing…
Mar 2026 · ensue-network.ai
13L8
Llama-8B Teaches Itself Baby Steps to Deep Research Using RL▲39
I've been tinkering with getting Llama-8B to bootstrap its own research skills through self-play. The model generates questions about documents, searches for answers, and then learns from its own successes/failures through RL (hacked up Unsloth's GRPO code). Started with just 23% accuracy on Apollo 13 mission report questions and hit 53% after less than an hour of training. Everything runs locally using open-source models. It's cool to see the model go from completely botching search queries to iteratively researching to get the right answer.
2025 · github.com
14AP
A Platform for Many-Agent Reinforcement Learning▲18
2017 · github.com
15RM
Rlpyt – Modular, Optimized Deep Reinforcement Learning in PyTorch▲7
2019 · github.com
16MG
Multi-GPU Reinforcement Learning in Tensorflow for OpenAI Gym▲58
2016 · github.com
17MZ
Model Zoo: Deploy your machine learning model in a single line of code▲34
2020 · modelzoo.dev
18AQ
AI QLearning Robot Simulation in JavaScript and WebGL▲42
2015 · qlearning.4ck5.com
19TA
TensorForce: A TensorFlow library for applied reinforcement learning▲7
2017 · reinforce.io
20
I evaluated file, vector, graph and RL based memory frameworks▲13
An agent that remembers across sessions can keep its memory as curated markdown files, as an auto-mined structured store, or as trained experience.
22d ago · pinglin.tw
21RR
RLSL – Reinforcement Learning for Skip Lists (DBs and AI)▲9
2018 · github.com
22RL
Reinforcement Learning – DQN Tutorial▲6
2019 · youtube.com
23MA
Meta-agent: self-improving agent harnesses from live traces▲14
We built meta-agent: an open-source library that automatically and continuously improves agent harnesses from production traces. Point it at an existing agent, a stream of unlabeled production traces, and a small labeled holdout set. An LLM judge scores unlabeled production traces as they stream. A proposer reads failed traces and writes one targeted harness update at a time, such as changes to prompts, hooks, tools, or subagents. The update is kept only if it improves holdout accuracy. On tau-bench v3 airline, meta-agent improved holdout accuracy from 67% to 87%. We open-sourced meta-agent.…
Apr 2026 · github.com
24NR
New Reinforcement Learning Video Series▲11
2019 · youtube.com

Ranked by how close each launch is in meaning, then by votes. Refine with a description →