{
  "schema_version": "openagent.resource.v1",
  "id": "res_litert_lm",
  "slug": "litert-lm",
  "status": "published",
  "identity": {
    "name": "LiteRT-LM",
    "one_liner": "Google's open-source inference framework for deploying large language models on edge devices.",
    "short_description": "LiteRT-LM is Google's open-source, production-oriented inference framework for running LLMs on edge devices. It is relevant for teams evaluating local, mobile, and on-device agent stacks where latency, privacy, and hardware constraints matter."
  },
  "classification": {
    "resource_type": "model",
    "primary_category": "models",
    "subcategories": [
      "local-ai",
      "local-inference",
      "inference",
      "edge-ai",
      "on-device-ai"
    ]
  },
  "positioning": {
    "why_it_matters": "On-device agents need a model layer that can run close to the user. LiteRT-LM matters because it brings Google's edge AI work into an open-source framework for local LLM inference.",
    "best_for": [
      "Developers building on-device or edge AI applications",
      "Teams evaluating local LLM deployment for privacy-sensitive agents",
      "Researchers comparing mobile and embedded inference frameworks"
    ],
    "not_for": [
      "Teams that only need hosted API access to frontier models",
      "Users looking for a complete agent framework rather than an inference layer"
    ],
    "use_cases": [
      "local-ai"
    ],
    "target_audience": [
      "developer",
      "researcher"
    ],
    "maturity": "active"
  },
  "decision_signals": {
    "deployment_modes": [
      "local",
      "cloud"
    ],
    "open_source": true,
    "local_first": true,
    "self_hostable": false,
    "has_api": false,
    "has_gui": false,
    "supports_mcp": false,
    "supports_docker": false
  },
  "facts": {
    "license": "Apache-2.0",
    "pricing_model": "open_source",
    "github_stars": 5524,
    "github_forks": 571,
    "github_repo_full_name": "google-ai-edge/LiteRT-LM",
    "last_verified_at": "2026-06-10"
  },
  "capabilities": {
    "core_capabilities": [
      "local-inference",
      "inference"
    ],
    "interfaces": [
      "repo"
    ]
  },
  "links": {
    "primary_url": "https://github.com/google-ai-edge/LiteRT-LM",
    "items": [
      {
        "type": "github",
        "label": "GitHub",
        "url": "https://github.com/google-ai-edge/LiteRT-LM"
      },
      {
        "type": "homepage",
        "label": "Homepage",
        "url": "https://ai.google.dev/edge/litert-lm"
      }
    ]
  },
  "media": {
    "thumbnail_url": "https://github.com/google-ai-edge.png",
    "og_image_url": "https://github.com/google-ai-edge.png",
    "thumbnail_brief": {
      "resource_type": "model",
      "visual_motif": "token grid, waveform, or chip abstraction",
      "background_style": "minimal editorial surface with restrained open-source accent color",
      "title_overlay": "LiteRT-LM",
      "subtitle": "Google's open-source inference framework for deploying large language models on edge devices.",
      "avoid": [
        "noisy poster layout",
        "large marketing slogans",
        "random gradient blobs"
      ]
    }
  },
  "tags": {
    "category": [
      "model",
      "open-source"
    ],
    "capability": [
      "local-inference",
      "inference"
    ],
    "constraint": [
      "open-source",
      "local-first"
    ],
    "scenario": [
      "local-ai"
    ]
  },
  "relationships": {},
  "machine_readable": {
    "canonical_url": "https://www.openagent.bot/models/litert-lm",
    "json_url": "https://www.openagent.bot/models/litert-lm.json",
    "markdown_url": "https://www.openagent.bot/models/litert-lm.md"
  },
  "seo": {
    "title": "LiteRT-LM: Open-Source Edge LLM Inference Framework",
    "description": "LiteRT-LM is Google's open-source framework for deploying large language models on edge and on-device environments."
  },
  "editorial": {
    "trust_note": "Verified from source links and project metadata.",
    "core_strengths": [
      {
        "title": "Edge-first inference",
        "description": "LiteRT-LM focuses on deploying LLMs on edge and on-device environments.",
        "why_it_matters": "Local inference can reduce latency, preserve privacy, and keep agents useful when cloud access is constrained."
      },
      {
        "title": "Google AI Edge ecosystem",
        "description": "The project sits under Google's AI Edge GitHub organization.",
        "why_it_matters": "Teams already watching Google's mobile and edge AI stack get a relevant open-source inference option to evaluate."
      },
      {
        "title": "Production-oriented model serving",
        "description": "The repository describes LiteRT-LM as a production-ready inference framework.",
        "why_it_matters": "Agent builders need model layers that can move beyond notebooks and into real devices."
      }
    ],
    "use_case_notes": [
      {
        "title": "On-device assistants",
        "description": "Evaluate LiteRT-LM when an assistant needs local responses on mobile, desktop, or embedded hardware."
      },
      {
        "title": "Private local inference",
        "description": "Use edge deployment to reduce dependence on cloud APIs for sensitive workflows."
      },
      {
        "title": "Model runtime comparison",
        "description": "Compare LiteRT-LM with other local inference projects before choosing an agent model layer."
      }
    ],
    "compare_notes": [
      {
        "title": "When to choose LiteRT-LM",
        "summary": "Compare it with nearby models by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need."
      }
    ],
    "getting_started": [
      {
        "label": "Open the GitHub repository",
        "url": "https://github.com/google-ai-edge/LiteRT-LM",
        "type": "github"
      },
      {
        "label": "Read the project docs",
        "url": "https://ai.google.dev/edge/litert-lm",
        "type": "docs"
      }
    ],
    "seo_article": {
      "intro": "LiteRT-LM is Google's open-source inference framework for deploying large language models on edge devices.",
      "what_it_is": "It is a model runtime layer for local and on-device LLM applications rather than a complete agent framework.",
      "why_it_matters": "As agents move closer to devices, local inference becomes a core deployment choice.",
      "how_it_works": "Start from the official repository and documentation, then evaluate latency, supported models, device targets, and integration fit.",
      "faq": [
        {
          "question": "Is LiteRT-LM open source?",
          "answer": "Yes. The GitHub repository is listed under the Apache-2.0 license."
        },
        {
          "question": "Who should evaluate LiteRT-LM?",
          "answer": "Teams building edge, mobile, desktop, or privacy-sensitive AI applications should evaluate it."
        }
      ]
    }
  },
  "timestamps": {
    "created_at": "2026-06-10T00:00:00.000Z",
    "updated_at": "2026-06-10T00:00:00.000Z",
    "published_at": "2026-06-10T00:00:00.000Z"
  }
}