Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
☆1,362Jul 4, 2026Updated 4 months ago
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:
- Our library for RL environments + evals☆4,764Updated this week
- Agentic RL Training at Scale☆2,215Updated this week
- An open infrastructure to democratize and decentralize the development of superintelligence for humanity.☆975Mar 24, 2026Updated 7 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆509Sep 27, 2024Updated 2 years ago
- ☆1,495Dec 22, 2025Updated 10 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,544Apr 17, 2026Updated 6 months ago
- Axolotl Plugin integrating with Nous Research's Atropos☆14Jul 17, 2025Updated last year
- Standalone repo for our Atropos integration with Thinking Machines Tinker API (https://thinkingmachines.ai/tinker/)☆102Mar 22, 2026Updated 7 months ago
- Distributed Training Over-The-Internet☆1,065Oct 14, 2025Updated last year
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,495Updated this week
- Lightly-reviewed collection of community environments☆264Sep 7, 2026Updated last month
- Scalable toolkit for efficient model reinforcement☆2,105Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,908Oct 16, 2026Updated 2 weeks ago
- ☆203Dec 18, 2025Updated 10 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.
- A Gym for Agentic LLMs☆514Jan 21, 2026Updated 9 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,451Updated this week
- slime is an LLM training framework for RL Scaling.☆8,786Updated this week
- ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA☆5,630Jun 17, 2026Updated 4 months ago
- Go ahead and axolotl questions☆12,667Updated this week
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,839Updated this week
- An interface library for RL post training with environments.☆2,829Updated this week
- MoE training for Me and You and maybe other people☆401Mar 15, 2026Updated 7 months ago
- Ludic – an LLM-RL library for the era of experience☆66Aug 9, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- AllenAI's post-training codebase☆3,924Updated this week
- Entropy Based Sampling and Parallel CoT Decoding☆3,434Nov 13, 2024Updated last year
- Tools for merging pretrained large language models.☆7,430Updated this week
- PyTorch-native post-training at scale☆705Sep 9, 2026Updated last month
- A PyTorch native library for large model training☆30Apr 1, 2026Updated 7 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,023Oct 22, 2026Updated 2 weeks ago
- A framework for optimizing DSPy programs with RL☆339Jan 12, 2026Updated 9 months ago
- Puffing up reinforcement learning☆6,579Oct 14, 2026Updated 3 weeks ago
- Minimalistic large language model 3D-parallelism training☆2,854Oct 8, 2026Updated 3 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrast…☆343Updated this week
- Maybe the new state of the art vision model? we'll see 🤷♂️☆206Jan 10, 2024Updated 2 years ago
- Synthetic data curation for post-training and structured data extraction☆1,763Updated this week
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆112Mar 7, 2025Updated last year
- Build RL environments for LLM training☆28Sep 15, 2026Updated last month
- DSPy: The framework for programming—not prompting—language models☆38,904Updated this week
- Train transformer language models with reinforcement learning.☆19,669Updated this week