AI · alternatives · 2026
24 alternatives to Terminal-Bench-RL: Training long-horizon terminal agents with RL
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…
Terminal-Bench-RL is an infrastructure for training reinforcement learning agents to perform complex terminal and coding tasks over long horizons. It uses Docker-isolated training environments and a hybrid reward… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes.
- 1
RL-training an AI agent to RL-train AI agents. Contribute to Danau5tin/ai-trains-ai development by creating an account on GitHub.
Jul 2026 · github.com · its alternatives →
- 2Agent 37▲401
Hey HN, I noticed there are 1,000+ MCP skills on GitHub with zero way for creators to charge for them. So I built Agent37. Selling Claude skills today means asking customers to download your skill, set up Claude Code on their laptops, configure MCP servers, and pray it works. No trial, no updates, often you're just handing over the source. Agent37 lets creators upload a skill, share a link, and anyone can try it instantly (no Claude account needed). Built-in Stripe, creators keep 80%. Looking for feedback on the approach. Would you use something like this?
Mar 2026 · agent37.com · its alternatives →
- 3
Superset▲541Hey HN, we’re Avi, Kiet, and Satya. We’re building Superset, an open-source terminal made for managing a bunch of coding agents (Claude Code, Codex, etc) in parallel. - Superset makes it easy to spin up git worktrees and automatically setup your environment - Agents and terminal tabs are isolated to worktrees, preventing conflicts - Built-in hooks [0] to notify when your coding agents are done/needs attention, - A diff viewer to review the changes and make PRs quickly We’re three engineers who’ve built and maintained large codebases, and kept wanting to work on as many features in…
Feb 2026 · superset.sh · its alternatives →
- 4
Scored 65.2% vs google's official 47.8%, and the existing top closed source model Junie CLI's 64.3%. Since there are a lot of reports of deliberate cheating on TerminalBench 2.0 lately (https://debugml.github.io/cheating-agents/), I would like to also clarify a few things 1. Absolutely no {agents/skills}.md files were inserted at any point. No cheating mechanisms whatsoever 2. The cli agent was run in leaderboard compliant way (no modification of resources or timeouts) 3. The full terminal bench run was done using the fully open source version of the agent, no…
Apr 2026 · github.com · its alternatives →
- 5
Hola HN! Long time lurker, sometimes commentor, first time poster here. I’ve been working alongside my two co-founders and a few colleagues on a project I’m excited (and a little nervous) to share with you all! Like many of us, I’ve lived a tortured existence with AI coding (is it vibes?) over the past few months - I think November was a big moment with this. But, one thing I’ve noticed after building orchestration layer after orchestration layer is that the thing I always came back to was “what the hell is Claude Code actually doing?” Perhaps it’s because of the time Claude Code got…
Jun 2026 · backplanes.com · its alternatives →
- 6
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
Feb 2026 · github.com · its alternatives →
- 7
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 · its alternatives →
- 8
Fabraix▲196We built Adversarial Cost to Exploit (ACE), a benchmark that measures the token expenditure an autonomous adversary must invest to breach an LLM agent. Instead of binary pass/fail, ACE quantifies adversarial effort in dollars, enabling game-theoretic analysis of when an attack is economically rational. We tested six budget-tier models (Gemini Flash-Lite, DeepSeek v3.2, Mistral Small 4, Grok 4.1 Fast, GPT-5.4 Nano, Claude Haiku 4.5) with identical agent configs and an autonomous red-teaming attacker. Haiku 4.5 was an order of magnitude harder to break than every other model; $10.21 mean…
May 2026 · fabraix.com · its alternatives →
- 9
We built a computer use agent once and got it benchmarked at the 2nd position in the biggest benchmark for this field but in the process, we realized one thing, how outdated and inefficient these benchmarks are and how they don't truly capture how these tasks went. So we thought a community led benchmarking arena would be the way to go about. https://coarena.ai/. You just have to put in a task and two side by side windows with hidden models will show up and do the same task and at the end you vote which one did better(or none). We have a leaderboard where we rank all the…
Aug 2026 · coarena.ai · its alternatives →
- 10RE
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 · its alternatives →
- 11
AgentGrid▲77Hi HN, I’m Michael, I built AgentGrid with my friend Souren because we were tired of losing our coding sessions and couldn't keep track of what was actually being built across our many projects. Our approach was to use an infinite canvas desktop app for the TUIs we already know and love, mainly claude + codex. We drew inspiration from Figma and Railway. Overtime we added image nodes, notes, terminals, coding editors, source control, etc. I wasn't sure about it at first. It took me a month to give the first version Souren built a real try. What got me was an Apple System Update I've been…
Jul 2026 · agentgrid.sh · its alternatives →
- 12
When we asked developers from large engineering teams, almost everyone is using Claude Code, Cursor, or Copilot. But adoption is still inconsistent. Some of us would have 15 agents running in Claude Code at the same time; some would still refuse to use any of them and write code manually. There's a fragmented AI development problem: - Five developers building similar features, and all of them start from scratch - No way to share "here's how we prompt AI to follow our architecture" - No trail of how the AI changes were generated - People leave the company, so does the their knowledge Aviator…
2025 · aviator.co · its alternatives →
- 13
This weekend I built a multi-agent coding system which, quite unexpectedly, beat Claude Code on Stanford's Terminal Bench! The architecture is straightforward, consisting of an orchestrator agent that deploys explorer & coder subagents to complete complex terminal based tasks, utilising an intelligent context sharing mechanism along the way which makes it all work. The repo has a lot of technical details, and all the code and prompts for you to play around with if you'd like! I had a lot of fun making this, I hope you have fun reading the README, using it yourself, or even extending it! As…
2025 · github.com · its alternatives →
- 14IN
Tl;dr: I trained a classifier to route to the least expensive model and reasoning depth to complete the request. Coupling that with additional automated token efficiency techniques has yielded 3x usage for the same spend. For anyone interested in trying it themselves: https://nerfguard.com Various teammates and I switched over to Codex from Claude Code recently. We still bounce between the tools, but Codex’s speed and steerability coupled with performance gains were hard to ignore. One of the downsides was that the per token pricing kicked in way sooner. This is happening across…
Jun 2026 · its alternatives →
- 15
We were both genuinely impressed by Claude Code after it helped each of us fix nasty CI problems overnight. Doing those fixes manually would have taken days. After that experience, we each found ourselves struggling through Ctrl+Tab through multiple Claude Code windows in our terminals. While we enjoyed having agents working for us in parallel, context switching and cycling through each terminal tab was a real pain. So we thought: Can we design a TUI dashboard that manages a large swarm of agents in one place? Even better, can agents manage agents hierarchically, like how companies work?…
May 2026 · omar.tech · its alternatives →
- 16
I'm Josh, founder of Synth. We've been working on coding agent optimization with method like GEPA and MIPRO (the latter of which, I helped to originally develop), agent evaluation via methods like RLMs, and large scale deployment for training and inference. We've also worked on patterns for memory, processing live context, and managing agent actions, combining it all in a single stack called Horizons. With the release of OpenAI's Frontier and the consumer excitement around OpenClaw, we think the timing is right to release a v0. It integrates with our sdk for evaluation and optimization but…
Feb 2026 · github.com · its alternatives →
- 17
We’re excited to share ML-Dev-Bench, a new open-source benchmark that tests AI agents on real-world ML development tasks. Unlike typical coding challenges or Kaggle-style competitions, our benchmark simulates end-to-end ML workflows including: - Dataset handling and preprocessing - Debugging model and code failures - Implementing new model architectures - Fine-tuning and improving existing models With 30 diverse tasks, ML-Dev-Bench evaluates agents across critical stages of ML development. To complement this, we built Calipers, a framework that provides systematic performance evaluation and…
2025 · github.com · its alternatives →
- 18
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.
Aug 2026 · github.com · its alternatives →
- 19
One terminal. Every agent. Total clarity.
May 2026 · github.com · its alternatives →
- 20
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 · its alternatives →
- 21BA
I'm one of the creators of The Edge Agent (TEA). We built this because we needed a way to deploy agents that was verifiable and robust enough for production/edge cases, moving away from loose scripts. The architecture aims to solve critical gaps in deterministic orchestration identified by *Prof. Claudionor Coelho Jr. (Stanford alum, ML/DL Faculty at Santa Clara Univ., and Senior Fellow for AI at Majestic Labs)* during our work on the Kiroku project. *Key Technical Features:* * *Neurosymbolic Native:* We integrated Prolog to logically validate LLM outputs. This combines neural…
Jan 2026 · fabceolin.github.io · its alternatives →
- 22
Hi HN folks, I have been building AI agents for quite some time now. The shift has gone from LLM + Tools → LLM Workflows → Agent + Tools + Memory, and now we are finally seeing true agency emerge: agents as systems composed of tools, command-line access, fine-grained system capabilities, and memory. This way of building agents is powerful, and I believe it is here to stay. But the real question is: are the systems powering these agents ready for that future? I do not think so. Using Docker for a single agent is not going to scale well, because agents need to be lightweight and fast. LLMs…
Mar 2026 · github.com · its alternatives →
- 23RA
Hey everyone! Along with my team, I've developed a reinforcement learning system that automatically optimizes LLM prompts, complete with a visualization feature to track both prompt structure and learning progress over time. Take a look here: https://nomadic-ml.github.io/nomadic/cookbooks/Nomadic_Promp... Check out our website too:https://www.nomadicml.com/ In terms of how this visualization works: The RL Prompt Optimizer employs a reinforcement learning framework to iteratively improve prompts used for language model evaluations. At each episode, the…
2024 · nomadic-ml.github.io · its alternatives →
- 24
I want to share a new dataset of 331 reward-hackable environments. These are real environments used in Terminal Bench and adjacent benchmarks. I first got interested in this because, as a reviewer of Terminal Bench, I noticed a lot of our tasks were hackable. I also noticed that many contributors to the benchmark do so because it provides credibility when selling environments to labs. Hence, TBench tasks are, in my opinion, held to a higher quality standard than those being used today for RL. No one is spending hours manually reviewing the $1B in tasks being purchased by major labs. As far…
Apr 2026 · github.com · its alternatives →
Also compare
- I RL-trained an agent that trains models with RL (for ~$1.3k) alternatives
- Agent 37 alternatives
- Superset alternatives
- OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview alternatives
- Spotlight by Backplanes alternatives
- 20+ Claude Code agents coordinating on real work (open source) alternatives
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →