Alternatives
Products that do what Terminal-Wrench, a dataset of 331 realistic hackable environments does
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…
- 1OA
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
- 2TB
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
- 3FA
I built Fresh to challenge the status quo that terminal editing must require a steep learning curve or endless configuration. My goal was to create a fast, resource-efficient TUI editor with the usability and features of a modern GUI editor (like a command palette, mouse support, and LSP integration). Core Philosophy: - Ease-of-Use: Fundamentally non-modal. Prioritizes standard keybindings and a minimal learning curve. - Efficiency: Uses a lazy-loading piece tree to avoid loading huge files into RAM - reads only what's needed for user interactions. Coded in Rust. - Extensibility: Uses…
Dec 2025 · sinelaw.github.io
- 4TC
Looking to get some feedback from the Hacker News community. I wrote the book with a focus on penetration testers and red teamers, but there are great examples for network admins, developers, and blue team defenders as well. You can pick up a copy for free here through May 19, 2019: https://gumroad.com/l/the_cyber_plumbers_handbook/hackernews... Please note, because it's hosted on Gumroad, it does require an email. If you don't want to give out your actual email, check out an anonymous email service. I give it away to students for free, so if you know of one that…
2019
- 5
hackerDen▲77Collaborative hackathon workspace with visible contributions
May 2026 · hackerden.netlify.app
- 6RU
hey all, happy to share research i've been working on for islo.dev in recent months. ever since the cheating agents (https://debugml.github.io/cheating-agents/) paper came out, revealing reward hacking was 4x more prevalent than previously estimated, i've been looking into how we can deal with the issue the common approach (taken by the tbench team) is post hoc trajectory analysis. i've been interested in the idea of reframing the problem as an endpoint security problem and tackling it via sandbox i hope you find it interesting, and thanks to the islo.dev team for…
Jun 2026 · github.com
- 7CH
2016 · code.hackmit.org
- 8MA
I've been exploring the (not so=) amazing potential of AI in coding and have compiled a list of tools. From AI-powered IDEs to code generators, this resource is my contribution to the community. I'm still on the fence about including txt2sql projects, as their functionality seems too basic to me. And I'm personally maintaining this, so your feedback is wellcome.
2025 · aicode.danvoronov.com
- 9AA
2018 · amp.rs
- 10TR
Hi HN, Today I'm showcasing Trunchbull, a benchmarking platform designed for authoring benchmarks and running them against different models. We have direct support for benchmarks that use the harbor authoring system, custom tool authoring via the vercel ai sdk and configuration limits. We've also already imported terminalbench 2.0, as a sort of proof of concept that our harbor task orchestrator works, although you currently need a paid account as we are provisioning sandbox environments. I've made several popular benchmarks publicly available for testing. You dont need an account or your…
25d ago · trunchbull.dev
- 11HA
This project is a tool for engineers who live in the terminal and are tired of losing their command history to ephemeral servers or fragmented `.bash_history` files. If you’re jumping between dozens of boxes, many of which might be destroyed an hour later, your "local memory" (the history file) is essentially useless. This tool builds a centralized, permanent brain for your shell activity, ensuring that a complex one-liner you crafted months ago remains accessible even if the server it ran on is long gone. The core mechanism wants to be a "zero-touch" capture that happens at the connection…
Jan 2026 · github.com
- 12
Every single day of my life since I started programming back in 2020 I open my projects through the terminal/ghostty. "cd path" + "code .". Until today I don't even know how to open vscode first then open a project from there. I usually have 3-4 vscode windows open at the same time, and I like them in separate desktops (for mac users). i gotta admit, i use 8 desktops, 3-4 for vscode, 1 for arc, 1 for docker, 1 for postman etc. So my daily routine when I turned on my mac was: (1) open ghostty; (2) cd-path+code.; (3) drag the vscode window to a desired desktop; (4) get back to the ghostty…
Aug 2026 · github.com
- 13MS
A little over a year ago I gave away over 4,600 copies of my intro to SSH tunneling book, The Cyber Plumber's Handbook, for free over a 48 hour period to the awesome folks here on Hacker News (https://news.ycombinator.com/item?id=19946941). Since then, I've been getting a lot of feedback about creating an interactive lab where SSH tunneling and port redirection techniques can be practiced in real scenarios. With a bit more time during the quarantine, I finally found the time to launch the lab portion. For the HN family, I'm offering the book and 2 weeks of lab time for 50% off…
2020
- 14HN
I put this together since I find myself switching away from the terminal to see if anything new popped up in HN. There might be similar ones out there, didn't bother looking. It was a quick experiment, which might end up with a few more features.
2011 · github.com
- 15GF
Just open-sourced a small terminal tool I’ve been working on. The idea came from wondering how useful it’d be if you could just describe the kind of dataset you need, and it would go out, do the deep research, and return something structured and usable. You give it a description, and it pulls relevant info from across the web, suggests a schema based on what it finds, and generates a clean dataset. The schema is editable, and it also adds a short explanation of what the dataset covers. In some cases, it even asks follow-up questions to make the structure more useful. Started off as a quick…
2025 · github.com
- 16TI
I'm an "ideas person" who messes around with AI on a low budget. I got tired of watching my tokens vanish and context windows filling up while agents fumbled around trying to find the right thing. Agents don't flail like they used to with shell tools, but there are still weak/blind spots and back-and-forth episodes — especially when using tools in combination/sequence. So I built "tilth" today. Or rather, AI built it — every line is Opus 4.6. I spent a lot of my precious tokens getting it to "not shit" (at least several of the different vendors' AI overlords assure me it's not…
Feb 2026 · github.com
- 17
- 18IV
So, I've never written a line of Rust in my life. I wouldn't know an `&mut this` from a mutandis. But I saw a tweet about a month ago that said, in this new era of AI, you'd be able to just take a library that you love, throw a TUI around it, and call it an app. So I spent about 200 bucks last month, here's what I came up with: Imbolc is a DAW that runs entirely in your terminal. It talks to scsynth over OSC and ships 58 instruments and 39 effects. VSTs are a work in progress, also GarageBand loops if you want to recreate "Umbrella". The codebase is about 60k? lines of Rust across 5 crates,…
Feb 2026 · github.com
- 19IM
Hello HackerNews, I'm Kaamkiya, the author of this program. It's a collection of minimal games made for terminals, like 2048, Hangman, and even two player games like pong. They're all text-based, but they can actually be quite fun. If you want to test it right now, you can do this: go run github.com/Kaamkiya/gg@latest I started this project out of boredom, honestly. I was bored, and when I'm bored I like to code or play video games. So I coded video games. I kept them really minimal though, because I'm not great at gamedev and thought it would be easier to contribute to text-based…
2024 · github.com
- 20AA
I’ve had this idea for a new code editor chord grammar bouncing around in my head for over 2 years, and now I can finally release v0.1 of ane. You can run it one-shot from scripts or agents (`ane exec —chord…`) or use its full-on TUI editor. ane is pure Rust, and integrates tree-sitter and LSP to provide a pleasant and predictable terminal code editing experience. I’d love folks to try it out and give feedback! Thanks :)
May 2026 · github.com
- 21TN
Hi guys, I’m excited to share an update on ReproModel, an open-source toolbox designed to streamline the testing and reproduction of machine learning models. I, like many of you, have really struggled with benchmarking and comparing models, from missing code, to opaque experiment parameters slowing the process. I decided to take matters into my own hands, and created a mini-toolbox in my free time to streamline the process. The goal is to reduce the time and effort spent on replicating experiments, enabling researchers to focus on innovation rather than setup. Knowing this task is not an…
2024 · github.com
- 22UI
Hey everyone! I am excited to share updates on four of my & my teams' open-source projects that take large-scale search systems to the next level: USearch, UForm, UCall, and StringZilla. These projects are designed to work seamlessly together, end-to-end—covering everything from indexing and AI to storage and networking. And yeah, they're optimized for x86 AVX2/512 and Arm NEON/SVE hardware. USearch [1]: Think of it as Meta FAISS on steroids. It's now quicker, supports clustering of any granularity, and offers multi-index lookups. Plus, it's got more native bindings than probably…
2023 · usearch-images.com
- 23IB
I was experimenting with building a local dataset generator with deep research workflow a while back and that got me thinking. what if the same workflow could run on my own files instead of the internet. being able to query pdfs, docs or notes and get back a structured report sounded useful. so I made a small terminal tool that does exactly that. I point it to local files like pdf, docx, txt or jpg. it extracts the text, splits it into chunks, runs semantic search, builds a structure from my query, and then writes out a markdown report section by section. it feels like having a lightweight…
2025 · github.com
- 24AC
I built this toolkit with my colleague to dive deep into OS internals and automate the identification of privilege escalation vectors. Written in pure C without external dependencies, it explores everything from Linux capabilities and Docker escapes to Windows token manipulation and service permissions. We believe that the constant struggle between breaking and securing systems is the ultimate driver of software evolution. This tool is our contribution to that cycle, designed for researchers who want to understand how low-level misconfigurations can be discovered and audited across different…
Jan 2026
Ranked by how close each launch is in meaning, then by votes. Refine with a description →