RULER – Easily apply RL to any agent
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…
RULER – Easily apply RL to any agent launched on July 11, 2025 with 81 votes, #500 of 9,223 launches that month and more than 95% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
RULER is a reward function tool that simplifies reinforcement learning for AI agents. Created by OpenPipe, it eliminates the need for task-specific labeled data and domain expertise by using an LLM judge to rank multiple action trajectories relative to each other. This approach avoids calibration problems common in LLM-based evaluation. The tool is designed for developers and teams looking to improve agent reliability through reinforcement learning without the typical implementation complexity.
written from the facts on this page · September 2026
From the sources
The OpenPipe platform has migrated to Weights & Biases and CoreWeave. Browse migration details and the OpenPipe technical archive.
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
Terminal-Bench-RL: Training long-horizon terminal agents with RL2025 · github.com · ▲125After 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…
ART – a new open-source RL framework for training agents2025 · github.com · ▲116Hey 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…
I RL-trained an agent that trains models with RL (for ~$1.3k)Jul 2026 · github.com · ▲107RL-training an AI agent to RL-train AI agents. Contribute to Danau5tin/ai-trains-ai development by creating an account on GitHub.
TesslFeb 2026 · tessl.io · ▲260I'm Guy, the founder behind Snyk — now building Tessl, a package manager for agent skills. We’ve recently witnessed that most teams still treat skills as static artifacts: markdown files, created or copied from repo to repo. This approach offers a strong initial boost, but quickly creates debt: - Skills are duplicated, and updates never roll out. - Poor quality skills go unseen, misguiding agents instead of helping. - Skill knowledge grows stale, and don’t keep up with the systems and practices they describe. Without a way to evaluate skills, teams have no clear way to understand how good a…
Supercharging RL with Hyper-Efficient Online Opt, +165% in 2h, $102025 · arc.computer · ▲32Arc enables continual learning for agents to adapt, learn, and transfer knowledge in live environments. Open-source SDK for building agents that learn from experience and improve over time.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, July 2025
the whole month →
Trickle - Magic Canvas ▲1,064Hey HN! Introducing Trickle Magic Canvas: the world’s first Agentic Canvas, where you can visually co-create apps and websites with AI, from idea to production. Why is a canvas better? Most AI tools today rely on linear chats or text prompts. We believe that limits creativity and clarity. Canvas changes the game. 1. Every version & page at a glance. Each page and sub-page lives on a timeline. You can quickly browse, edit, and preview progress like a living, visual document — no more digging through chat logs or scattered states. 2. The canvas is the context. Unlike linear chats, you can…
AI · 2025 · trickle.so
- TB
Life & fun · 2025 · trytender.app
Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…
Dev tools · 2025 · nodaysoff.run
Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https://www.morningbrew.com/issues/business-buzzkill), MetaFilter (https://www.metafilter.com/209703/Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…
AI · 2025 · drawafish.com
Hi HN - I made a site that takes a UK postcode, grabs the local MP's information and generates an AI mockup of what their ID might look like. It's a small, silly protest at the stupidity of the Online Safety Act that just came into force. edit - My open AI credits got hugged to death, please use a known postcode (like one from Kier Starmer's constituency, WC2B6NH) in the meantime.
AI · 2025 · use-their-id.com