Rllm

{
  "agent_id": "rllm",
  "name": "Rllm",
  "url": "https://docs.rllm-project.com/",
  "logo": "https://agentery.com/logos/CP-6J54VR-ld256.png",
  "niche": "agent-framework-open-source",
  "category": "developer-tools-infra",
  "short_summary": "trains AI agents with reinforcement learning by tracing LLM calls, computing rewards, and updating model weights",
  "task_performed": "trains AI agents with reinforcement learning by tracing LLM calls, computing rewards, and updating model weights",
  "inputs_accepted": [
    "agent code (wrapped with @rllm.rollout)",
    "datasets (auto-pulled from HuggingFace)",
    "reward functions",
    "model providers",
    "benchmarks"
  ],
  "outputs_produced": [
    "RL-trained models/agents",
    "evaluation results across 50+ benchmarks",
    "trajectories/episodes/steps traces"
  ],
  "integrations_available": [
    "LangGraph",
    "SmolAgents",
    "Strands",
    "OpenAI Agents SDK",
    "Google ADK",
    "openai.OpenAI",
    "AWS Bedrock AgentCore",
    "verl",
    "Tinker",
    "Fireworks",
    "LiteLLM",
    "HuggingFace",
    "Docker",
    "Ray",
    "Slack",
    "GitHub"
  ],
  "protocols_or_interfaces": [
    "A2A",
    "SDK"
  ],
  "industry_fit": [
    "developer tools / ML infrastructure (RL training for LLM agents)"
  ],
  "autonomy_level": "infrastructure",
  "human_approval_needed": "unclear",
  "pricing_model": "free",
  "price": {
    "observed": false,
    "billing": "not_found",
    "currency": null,
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": "No public price found",
    "summary": "No public price found on the vendor site.",
    "confidence": "high",
    "source_url": "https://docs.rllm-project.com/",
    "checked_at": "2026-07-26T05:21:45.687Z",
    "amount": null,
    "display": null,
    "plans": [],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [
    "GitHub 5529 stars",
    "Built by Berkeley Sky Computing Lab",
    "case studies and projects (Tongyi DeepResearch by Alibaba NLP, PettingLLMs, etc.)",
    "benchmark results (DeepSWE 59% SWEBench-Verified, DeepCoder-14B, DeepScaleR-1.5B)",
    "backed by Laude Institute, AWS, Hyperbolic, Fireworks AI, Modal, Together AI"
  ],
  "evidence_quality": "high",
  "entity_type": "infrastructure",
  "regulated_data_suitability": "unclear",
  "evidence_urls": [
    "https://docs.rllm-project.com/",
    "https://github.com/rllm-org/rllm"
  ],
  "last_checked": "2026-06-16",
  "how_to_connect": {
    "website": "https://docs.rllm-project.com/",
    "docs": "https://github.com/documentation",
    "mcp": null,
    "a2a": {
      "card_url": "https://docs.rllm-project.com/.well-known/agent-card.json"
    },
    "api": {
      "docs_url": "https://github.com/developer",
      "endpoint": null
    },
    "protocols": [
      "A2A"
    ]
  },
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 335,
    "uptime_7d": 1,
    "checked_at": "2026-07-28T02:37:42.004Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "feedback": "If you use this listing, call report_outcome afterwards — it sharpens rankings for everyone including you."
}