OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview

In plain words

OSS Agent is an open-source AI agent that achieved a 65.2% score on TerminalBench, outperforming Google's official implementation and the leading closed-source alternative. Built for developers and AI researchers, it executes terminal commands and tasks through an AI interface. The project is fully open-source and available on GitHub, with the maker emphasizing transparent evaluation without benchmark manipulation techniques.

written from the facts on this page · September 2026

From the sources

Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/ - dirac-run/dirac

In the maker’s words, at launch

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…

• 
  Agent 37Mar 2026 · agent37.com · ▲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?

• 
  Gemini CLI2025 · blog.google · ▲224

  A simple weekend project, to check if chat conversation could be used on CLI. Uses Google Gemini's gemini-2.0-flash model. Configs will make it nicer, but I wanted to keep it simple to test and launch for now. I can add things for you :) Please give it a try!

• 
  Terminal-Bench-RL: Training long-horizon terminal agents with RL2025 · github.com · ▲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…

• 
  Agent-desktop – Native desktop automation CLI for AI agentsMay 2026 · github.com · ▲99

  I've been building computer-use tools for a while, and I quietly launched this about a month ago (122 Stars on GH). I figured it was worth sharing here. Over the last few months, a lot of computer-use agents have come out: Codex, Claude Code, CUA, and others. Most of them seem to work roughly like this: 1. Take a screenshot 2. Have the model predict pixel coordinates 3. Click x,y 4. Take another screenshot 5. Repeat That works, but it's slow, expensive in tokens, and fragile. If the UI shifts a few pixels, things break. And the model still doesn't know what any element actually is. But the…

• 
  Coarena by CoastyAug 2026 · coarena.ai · ▲111

  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…

• 
  Horizons – OSS agent execution engineFeb 2026 · github.com · ▲39

  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…

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 30d ago · world.pixverse.video

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 4d ago · beam.win

• 
  Brila▲1,364

  One-page websites from real Google Maps reviews

  AI · Apr 2026 · brila.ai

• AG
  A game where you build a GPU▲964

  Thought the resources for GPU arch were lacking, so here we are

  Life & fun · Apr 2026 · jaso1024.com

• 
  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.

  AI · Apr 2026 · github.com

• 
  Fathom 3.0▲800

  AI meeting notes: now bot-free, in ChatGPT & Claude + more

  AI · Apr 2026 · fathom.ai

• 
  Brutalist Concrete Laptop Stand (2024)▲786

  I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay

  Life & fun · Apr 2026 · sam-burns.com

• 
  I built a frontpage for personal blogs▲783

  With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

  AI · Apr 2026 · text.blogosphere.app