{"slug": "rllm-shipped-an-update", "title": "rllm shipped an update", "summary": "The open-source reinforcement learning framework rllm, which trains language agents, shipped an update in July 2026. The project, hosted on GitHub with 5.7k stars, requires Python 3.11+ and supports multiple training backends.", "body_md": "# rllm\n\nDemocratizing Reinforcement Learning for LLMs\n\n## About rllm\n\nrLLM is an open-source framework for training language agents with reinforcement learning. Bring any harness, run it in any sandbox, and switch training backends with one flag — the same agent code drives both eval and training.\n\nrLLM requires Python >= 3.11. You can install it either directly via pip or build from source.\n\nThis installs dependencies for running rllm CLI with the tinker backend (single-machine, Tinker API). For other backends:\n\nrllm is an open-source project written primarily in Python, with 5.7k stars on GitHub. It was last updated in July 2026.\n\n```\nuv pip install \"rllm @ git+https://github.com/rllm-org/rllm.git\"\n```\n\n## rllm vs. the alternatives\n\n[All 30 alternatives →](/alternatives/rllm)", "url": "https://wpnews.pro/news/rllm-shipped-an-update", "canonical_source": "https://agentsearchengine.app/agents/rllm", "published_at": "2026-07-17 23:06:53+00:00", "updated_at": "2026-07-21 01:38:20.132644+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "developer-tools"], "entities": ["rllm", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/rllm-shipped-an-update", "markdown": "https://wpnews.pro/news/rllm-shipped-an-update.md", "text": "https://wpnews.pro/news/rllm-shipped-an-update.txt", "jsonld": "https://wpnews.pro/news/rllm-shipped-an-update.jsonld"}}