{"adoption": {"forks": 113, "observed_at": "2026-08-28T04:05:14.273118+00:00", "stars": 1633}, "canonical_url": "https://ross.abutalabs.com/products/agent-r1", "card": {"archived": false, "artifact_type": "framework", "description": "Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning", "domain": ["artificial-intelligence", "reinforcement-learning", "large-language-models", "machine-learning"], "enriched": true, "function": ["agent-framework", "llm-training", "reinforcement-learning", "machine-learning"], "health_score": 80, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["AgentR1/Agent-R1"], "name": "AgentR1/Agent-R1", "platform": ["python"], "pushed_at": "2026-08-24T18:10:46+00:00", "repo": "AgentR1/Agent-R1", "stars": 1633, "tags": ["agentic-rl", "step-level-mdp", "tool-use", "multi-step-agents", "policy-optimization", "online-policy-distillation", "ai-agents", "gpu", "linux"], "topics": ["agent", "agentic-rl", "llm"], "urls": [], "use_cases": ["train an LLM agent to use tools via reinforcement learning", "run multi-step agentic RL with environment feedback", "fine-tune models on HotpotQA, ALFWorld, or WebShop agent tasks", "apply StepPO-style step-level policy optimization", "perform online policy distillation for agents", "build custom agentic RL training environments"], "what_it_is": "Agent-R1 is a modular Python framework for training LLM agents with end-to-end reinforcement learning. It models each interaction turn as a step-level MDP transition, making tool use, environment feedback, context management, and reward assignment explicit parts of the training loop.", "when_to_avoid": ["you only need single-turn RLHF or DPO fine-tuning without agent interaction", "you need a production inference or agent-serving framework rather than a training framework", "you lack GPU resources for RL training"], "when_to_choose": ["you need step-native RL training for multi-turn LLM agents rather than single-turn pipelines", "you want explicit control over tool use, context management, and reward assignment during training", "you want a research framework with recipes for standard agent benchmarks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/agent-r1", "repo": "AgentR1/Agent-R1", "role": "main", "score": 65}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.273118+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:47:10.284793+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0ecfc7b21d795553056e649ad1fa90ea98a2e092f7a8a8a74cd9fbfb0d1de29b", "fetched_at": "2026-08-28T04:05:14.273118+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AgentR1/Agent-R1"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 39, "rhythm": 35}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 548, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 65, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}