Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
☆914Mar 20, 2026Updated this 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:
- Async RL Training at Scale☆1,176Updated this week
- Our library for RL environments + evals☆3,918Updated this week
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆465Sep 27, 2024Updated last year
- An open infrastructure to democratize and decentralize the development of superintelligence for humanity.☆635Updated this week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,368Mar 15, 2026Updated last week
- 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.
- Distributed Training Over-The-Internet☆984Oct 14, 2025Updated 5 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☆1,713Updated this week
- Entropy Based Sampling and Parallel CoT Decoding☆3,434Nov 13, 2024Updated last year
- Standalone repo for our Atropos integration with Thinking Machines Tinker API (https://thinkingmachines.ai/tinker/)☆20Updated this week
- ☆33Dec 15, 2025Updated 3 months ago
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆9,050Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,259Updated this week
- Exploring Applications of GRPO☆252Aug 25, 2025Updated 7 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.
- MoE training for Me and You and maybe other people☆381Mar 15, 2026Updated last week
- Go ahead and axolotl questions☆11,508Updated this week
- DeMo: Decoupled Momentum Optimization☆198Dec 2, 2024Updated last year
- Tools for merging pretrained large language models.☆6,895Mar 15, 2026Updated last week
- ☆137Mar 20, 2025Updated last year
- ☆19Mar 16, 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…☆3,131Mar 16, 2026Updated last week
- Asynchronous P2P communication backend for decentralized pipeline parallelism☆42Jun 9, 2025Updated 9 months ago
- Automatic evals for LLMs☆583Feb 24, 2026Updated last month
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆639Jan 29, 2026Updated last month
- Efficient Triton Kernels for LLM Training☆6,216Mar 18, 2026Updated last week
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆253Oct 30, 2024Updated last year
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆652Jul 29, 2025Updated 7 months ago
- Minimalistic large language model 3D-parallelism training☆2,617Feb 19, 2026Updated last month
- Simplifying reinforcement learning for complex game environments☆5,199Updated this week
- A Gym for Agentic LLMs☆467Jan 21, 2026Updated 2 months ago
- Scalable toolkit for efficient model reinforcement☆1,447Updated this week
- AllenAI's post-training codebase☆3,643Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Train your own SOTA deductive reasoning model☆108Mar 6, 2025Updated last year
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆382Updated this week
- ☆122May 19, 2024Updated last year
- ☆338Mar 5, 2026Updated 3 weeks ago
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆679Mar 16, 2025Updated last year
- DSPy: The framework for programming—not prompting—language models☆33,038Updated this week
- prime is a framework for efficient, globally distributed training of AI models over the internet.☆851Nov 16, 2025Updated 4 months ago