Atropos

license

MIT(OSI)

source

public

scope

async RL-environments framework + trajectory API

trainer-integrations

Axolotl/Tinker

core features withheld

no

MIT-licensed, an OSI license, with the source public and no managed or closed core. It sits in this category as the RL-training-environment layer beneath RLHF, RLAIF and GRPO training runs.

• https://api.github.com/repos/NousResearch/atropos recorded 2026-09-09

  Repository JSON: "private": false, "visibility": "public", "archived": true, "disabled": false, "spdx_id": "MIT", "pushed_at": "2026-07-04T17:39:01Z", "open_issues_count": 0, default_branch main, created 2025-04-29. Corroborates the landing page on both the public-source and the MIT reading, and independently confirms the archived flag the warehouse GitHub signal reported.

• https://github.com/NousResearch/atropos recorded 2026-09-09

  Repo page carries the label "Public archive" and the banner "This repository was archived by the owner on Jul 4, 2026. It is now read-only." Embedded repo JSON reads "isPrivate":false and "isArchived":true alongside "license":{"spdxId":"MIT","name":"MIT License"}. The rendered README says "Atropos is an environment microservice framework for async RL with LLMs." and its Navigating the Repo table lists the product's own parts in-repo: atroposlib/ ("Core library containing base classes and utilities"), environments/ ("Collection of ready-to-use RL environments"), example_trainer/ ("Example training scripts and configurations"); installation is "pip install atroposlib" or an editable install of the same tree. So the published repo is the runnable product: source public. For core-gated I extracted the rendered README text out of the saved body (21,019 characters) and searched it for enterprise, pricing, paid, commercial, subscription, premium, cloud tier, license key, sign up, contact sales and managed: zero hits on all of them except one occurrence of "managed", which is the ManagedServer class documentation link. Nothing in the repo is withheld for a paid tier.

• https://nousresearch.com/ recorded 2026-10-14

  Vendor home page, redesigned since the prior read (890,639 bytes vs. 76,131). Nav now covers Hermes Agent, Nous Portal, Business/Enterprise and Plans (Hermes Enterprise on-prem/cloud, subscription management at portal.nousresearch.com/manage-subscription); Psyche, Hermes 4, Chat and Simulators no longer appear. Searching the raw body case-insensitively: atropos and pricing are still zero hits; enterprise, subscri and plan now return multiple hits, all tied to Hermes Agent/Nous Portal offerings, none naming Atropos. Atropos remains outside this vendor's commercial surface.

• https://portal.nousresearch.com/ recorded 2026-10-14

  The vendor's paid surface: a pricing page. It sells a Nous Portal subscription built around the Hermes agent: nav sections Overview, Hermes Cloud, Models, Plans, Resources, a Pricing heading, and copy about hosted tools that "come bundled with your subscription" and "bills to the same credits as your models". The string atropos (case-insensitive) does not occur anywhere in the saved body of 647,329 bytes, searched over the raw HTML rather than the rendered text so that script-embedded payloads were included. Nothing from the Atropos repo is sold as, or withheld for, a Portal tier.

• https://raw.githubusercontent.com/NousResearch/atropos/main/LICENSE recorded 2026-10-14

  The LICENSE body in full, 1,070 bytes. It opens "MIT License", carries "Copyright (c) 2026 Nous Research", and grants permission to deal in the software "without restriction" including use, copy, modify, merge, publish, distribute, sublicense and sell, subject only to the notice-retention condition and the standard warranty disclaimer. No field-of-use, non-commercial, competition or delayed-conversion clause anywhere in the text, so the recorded license:MIT(OSI) holds and resolves to the osi tier.

Adoption is measured by PyPI downloads of atroposlib, the package the repository installs. Nous Research archived the repository read-only on 2026-07-04, so this niche research download count is unlikely to grow further.

• https://api.github.com/repos/NousResearch/atropos recorded 2026-08-08

  stargazers_count 1343, forks_count 396, open_issues_count 0, archived true, pushed_at 2026-07-04T17:39:01Z. Corroboration only: attention at the low-thousands of stars on a repo that has stopped taking changes.

• https://pypi.org/pypi/atroposlib/json recorded 2026-08-08

  info.version 0.4.0, summary "Atropos: An Environment and Rollout handler for LLM RL", requires_python >=3.10, five releases (0.1.0, 0.2.0, 0.2.1, 0.3.0, 0.4.0) with the 0.4.0 files uploaded 2026-03-10T04:21:18Z. Two things matter here. First, the record's downloads object is present and filled with sentinels rather than absent: "downloads":{"last_day":-1,"last_month":-1,"last_week":-1}. It carries no figure; a reader that treats -1 as a count would band this product at nothing, and a reader that treats the key's presence as a figure is also wrong. Second, the 25,750-character long description is the repo README and links github.com/NousResearch/atropos, which is what ties the atroposlib download count to this product, since sources/products/atropos.yaml records no pypi artifact of its own.

• https://pypistats.org/api/packages/atroposlib/recent recorded 2026-08-08

  The whole 106-byte body is {"data":{"last_day":10,"last_month":157,"last_week":40},"package":"atroposlib","type":"recent_downloads"}. 157 downloads in the trailing 30 days for the package the README installs. Fetched 200 on the first attempt, no retry needed.

Atropos ships ready-made environments for dataset evaluation, games, judge-based RLHF and RLAIF, multi-turn RL, code execution and multimodal tasks, and it works with any OpenAI-compatible endpoint. It stops short of training itself: the trainer and inference engine come from elsewhere, such as Axolotl or Tinker, so it enables fine-tuning rather than performing it.

• https://raw.githubusercontent.com/NousResearch/atropos/main/README.md recorded 2026-09-28

  The README environment table lists "Dataset environments" with "GSM8K, MMLU, Custom HF Datasets", "Online environments" with "Blackjack, Taxi, Text-based games", "RLAIF and RLHF" with "LLM Judge/Reward Models", "Multi-Turn RL", "Code Execution" and "Multimodal". A Trainer Integrations section covers Axolotl and Tinker, and the diagram caption says "trainer & inference engine not included with the atropos package". Tooling includes "View Run (`view-run`)" and "Offline Data Generation" via atropos-sft-gen and atropos-dpo-gen, and "Atropos natively supports any model provider that adheres to the OpenAI API standard". Its results table reports "4.6x" on parallel tasks and 21% to 51.75% on simple tasks, self-reported. Searched the body for GRPO: none.