{"adoption": {"forks": 416, "observed_at": "2026-08-28T04:06:00.966973+00:00", "stars": 1975}, "canonical_url": "https://ross.abutalabs.com/products/prime-rl", "card": {"archived": false, "artifact_type": "framework", "description": "Agentic RL Training at Scale", "domain": ["reinforcement-learning", "large-language-models", "machine-learning", "gpu-computing", "artificial-intelligence"], "enriched": true, "function": ["llm-training", "reinforcement-learning", "machine-learning", "gpu-computing", "benchmarking"], "health_score": 100, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["PrimeIntellect-ai/prime-rl"], "name": "PrimeIntellect-ai/prime-rl", "platform": ["python", "cloud"], "pushed_at": "2026-08-26T19:54:30+00:00", "repo": "PrimeIntellect-ai/prime-rl", "stars": 1975, "tags": ["reinforcement-learning", "rlhf", "post-training", "sft", "vllm", "fsdp2", "slurm", "agentic-training", "moe", "distributed-training", "verifiers", "environments-hub", "multimodal", "fp8", "evals", "gpu", "linux", "docker", "kubernetes"], "topics": [], "urls": [], "use_cases": ["train LLMs with reinforcement learning at scale", "run agentic RL post-training on large MoE models", "fine-tune language models with SFT and RL pipelines", "deploy multi-node RL training jobs on Slurm or Kubernetes", "evaluate and post-train models on agentic environments like SWE", "train vision-language models with RL"], "what_it_is": "prime-rl is a Python framework for large-scale, fully asynchronous reinforcement learning training of language models, built on FSDP2 for training and vLLM for inference. It supports scaling to 1000+ GPUs, integrates with the Prime Intellect Environments Hub for agentic RL environments, and covers end-to-end post-training including SFT, RL, and evals.", "when_to_avoid": ["you only need simple single-GPU fine-tuning with minimal setup", "you need a lightweight RL library for small models or quick experiments", "you are not working with language models or agentic RL tasks", "you lack access to multi-GPU or multi-node infrastructure"], "when_to_choose": ["you need to scale RL training to hundreds or thousands of GPUs", "you want asynchronous, high-throughput agentic RL training", "you need integrated SFT, RL, and evaluation in one framework", "you want native integration with verifiers environments and the Environments Hub", "you need optimized support for large MoE models with expert and context parallelism"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/prime-rl", "repo": "PrimeIntellect-ai/prime-rl", "role": "main", "score": 87}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:00.966973+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:04:51.652278+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "71f2fe33a853a2bb6faa8f4aa974951c3538309a140c135438df74d630d91f89", "fetched_at": "2026-08-28T04:06:00.966973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PrimeIntellect-ai/prime-rl"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 40, "rhythm": 99}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 561, "days_push": 7, "days_rel": 8, "gap_med": 22.5, "n_releases_24m": 9}, "score": 87, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}