Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
☆1,012Apr 6, 2026Updated last week
Alternatives and similar repositories for atropos
Users that are interested in atropos are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Agentic RL Training at Scale☆1,292Updated this week
- Our library for RL environments + evals☆3,986Updated this week
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆479Sep 27, 2024Updated last year
- An open infrastructure to democratize and decentralize the development of superintelligence for humanity.☆673Mar 24, 2026Updated 3 weeks ago
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,391Mar 28, 2026Updated 2 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Distributed Training Over-The-Internet☆994Oct 14, 2025Updated 6 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆111Mar 7, 2025Updated last year
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,742Apr 8, 2026Updated last week
- Entropy Based Sampling and Parallel CoT Decoding☆3,431Nov 13, 2024Updated last year
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆9,157Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,402Updated this week
- ☆35Dec 15, 2025Updated 3 months ago
- Exploring Applications of GRPO☆252Aug 25, 2025Updated 7 months ago
- MoE training for Me and You and maybe other people☆380Mar 15, 2026Updated 3 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Go ahead and axolotl questions☆11,608Apr 8, 2026Updated last week
- Tools for merging pretrained large language models.☆6,973Mar 15, 2026Updated 3 weeks ago
- A PyTorch native library for large model training☆25Apr 1, 2026Updated last week
- Standalone repo for our Atropos integration with Thinking Machines Tinker API (https://thinkingmachines.ai/tinker/)☆44Mar 22, 2026Updated 3 weeks ago
- DeMo: Decoupled Momentum Optimization☆198Dec 2, 2024Updated last year
- ☆137Mar 20, 2025Updated last year
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,158Apr 6, 2026Updated last week
- ☆19Mar 16, 2025Updated last year
- Asynchronous P2P communication backend for decentralized pipeline parallelism☆44Jun 9, 2025Updated 10 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Puffing up reinforcement learning☆5,529Apr 5, 2026Updated last week
- Efficient Triton Kernels for LLM Training☆6,265Updated this week
- Automatic evals for LLMs☆585Feb 24, 2026Updated last month
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆647Jan 29, 2026Updated 2 months ago
- Minimalistic large language model 3D-parallelism training☆2,644Apr 7, 2026Updated last week
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆257Oct 30, 2024Updated last year
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆662Jul 29, 2025Updated 8 months ago
- AllenAI's post-training codebase☆3,683Updated this week
- Train your own SOTA deductive reasoning model☆109Mar 6, 2025Updated last year
- Deploy open-source AI quickly and easily - Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Scalable toolkit for efficient model reinforcement☆1,516Updated this week
- A Gym for Agentic LLMs☆476Jan 21, 2026Updated 2 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆394Updated this week
- Scalable RL solution for advanced reasoning of language models☆1,841Mar 18, 2025Updated last year
- ☆123May 19, 2024Updated last year
- ☆342Mar 5, 2026Updated last month
- prime is a framework for efficient, globally distributed training of AI models over the internet.☆854Nov 16, 2025Updated 4 months ago