The Duck: ARC-AGI-3 inference harness -- winning solution to ARC-AGI-3 Milestone 1.
☆105Jul 1, 2026Updated 4 months ago
Alternatives and similar repositories for duck-harness
Users that are interested in duck-harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ARC-AGI-3 Milestone 2 solution built on Tufa Labs’ Duck harness, with improved agent tools, compute scheduling, and SGLang serving.☆17Sep 30, 2026Updated last month
- ARC-AGI-3 Solver using Rendered Deterministic Moore Machines☆64Jul 29, 2026Updated 3 months ago
- ☆49Updated this week
- My submission to the ARC-AGI-3 Developer Preview Agent Compitition.☆95Jan 27, 2026Updated 9 months ago
- TELL: Test-time Experiential Lifelong Learning – a single LLM agent that learns from experience at test time, achieving 43.9% on ARC-AGI-…☆28Apr 29, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Use the Claude Code SDK to solve Arc AGI 3☆15Jul 18, 2025Updated last year
- ☆51Updated this week
- 3rd-place solution to the ARC-AGI-3 Preview Challenge — Explore It Till You Solve It☆22Jan 7, 2026Updated 9 months ago
- Frontier ARC-AGI-3 agent: 99.86% RHAE, all 183 levels solved for $654☆51Aug 11, 2026Updated 2 months ago
- ☆176Mar 26, 2026Updated 7 months ago
- Simple Python Game Engine☆30Jan 29, 2026Updated 9 months ago
- RL Environment and Benchmark pipeline. Code accompanying paper "Neurophysiologically Realistic Environment for Comparing Adaptive Deep Br…☆20Feb 6, 2026Updated 8 months ago
- NVARC solution to ARC-AGI-2☆155Jan 15, 2026Updated 9 months ago
- ☆11Sep 9, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Reverse Engineering the Abstraction and Reasoning Corpus☆363Feb 24, 2025Updated last year
- ☆12Dec 12, 2021Updated 4 years ago
- [ICML 2026] Code for Equilibrium Reasoners: learning attractor dynamics for scalable reasoning☆60Sep 14, 2026Updated last month
- ☆102Sep 24, 2026Updated last month
- ☆230Jan 5, 2026Updated 9 months ago
- Official implementation of "NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows"☆19Sep 22, 2025Updated last year
- ☆338Aug 3, 2026Updated 2 months ago
- Fing about with BFF and Friends.☆22May 16, 2024Updated 2 years ago
- Global Weather Forecasting from Mid-Range to Subseasonal Scale☆21Mar 26, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆145Aug 12, 2026Updated 2 months ago
- ☆58Nov 22, 2024Updated last year
- Vintix: Action Model via In-Context Reinforcement Learning - - —☆23May 23, 2025Updated last year
- ☆24Dec 15, 2025Updated 10 months ago
- 🏝️ Code for our paper: "Privasis: Synthesizing the Largest 'Public' Private Dataset from Scratch"☆16Jul 10, 2026Updated 3 months ago
- ☆29Oct 2, 2026Updated last month
- Code for the paper "Goals as Reward Producing Programs"☆14Dec 5, 2024Updated last year
- Time Series Representations with Hard-Coded Invariances Accepted at ICML2025☆13May 26, 2025Updated last year
- An XML-based video editor☆11Dec 23, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆13Aug 14, 2022Updated 4 years ago
- MICCAI 2022 Code for the paper: D'ARTAGNAN: Counterfactual Video Generation☆11Sep 28, 2022Updated 4 years ago
- Progress Prize winning submission for NVIDIA Nemotron Model Reasoning Challenge☆117Jun 19, 2026Updated 4 months ago
- ☆14Oct 5, 2024Updated 2 years ago
- ☆12Jul 21, 2024Updated 2 years ago
- [ICASSP23] "Visual Prompting for Adversarial Robustness" by Aochuan Chen*, Peter Lorenz*, Yuguang Yao, Pin-Yu Chen, and Sijia Liu☆12Aug 12, 2023Updated 3 years ago
- verl: Volcano Engine Reinforcement Learning for LLMs☆23Nov 6, 2025Updated 11 months ago