{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-09-19T19:09:41Z",
  "id": "com.gtmstacker.registry/tool/laya",
  "type": "tool",
  "slug": "laya",
  "canonical_url": "https://gtmstacker.com/registry/tool/laya/",
  "title": "Laya",
  "description": "Apache-2.0 local decision engine (Python, open weights) for classifying and scoring text without generating prose. It returns typed choices, ordinal scores and boolean probabilities in one forward pass, with presets for routing, guardrails, moderation and support triage. Three checkpoints cover English, multilingual and task-tuned work. The project reports 33 ms on a T4, but also discloses weak zero-shot performance on the base model and the need for domain calibration.",
  "category": "ai-infrastructure",
  "tags": [
    "ai-infrastructure",
    "classification",
    "model-routing",
    "support-triage",
    "self-hostable"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "1d77b5c2d8e12114f407f2dcf34125dd336ffb4327d69e13a4916a908a73c627",
  "date_published": "2026-09-19T00:00:00Z",
  "date_modified": "2026-09-19T00:00:00Z",
  "source": {
    "name": "github · NandhaKishorM/laya",
    "url": "https://github.com/NandhaKishorM/laya"
  },
  "license": "Apache-2.0",
  "one_liner": "Laya runs typed classification, scoring and confidence gates locally in one model pass, with separate English, multilingual and task-tuned checkpoints.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_model": "free",
  "who_its_for": "Teams routing support, lead, moderation or agent events that need a fast local classifier with explicit probabilities, rather than paying a generative model to produce and then parse text.",
  "aliases": [
    "laya",
    "Laya decision engine"
  ],
  "alternatives": [],
  "secondary_categories": [
    "marketing-ops",
    "chat-helpdesk"
  ],
  "last_verified": "2026-09-19",
  "evidence": {
    "claim_type": "mixed",
    "source_id": "https://github.com/NandhaKishorM/laya",
    "note": "Apache-2.0, Python package, open Hugging Face weights, three checkpoints, router behavior and the documented limits were confirmed from the repo and model card on 2026-09-19. Repo had ~846 stars and was pushed the same day; the Hugging Face English checkpoint had ~406 likes. Latency and benchmark figures are maker-reported T4 results, not independently reproduced here."
  },
  "caveats": "The maker's own benchmark says the base checkpoints are below the majority-class baseline on its typed-decisions set; the stronger result comes from the task-tuned checkpoint. Raw calibration needs temperature fitting on your domain, high-cardinality choices degrade, and multilingual routing must be selected before inference. Treat the published speed and accuracy as vendor claims until reproduced on your data and hardware.",
  "lead": "Apache-2.0 local decision engine for a narrow job generative models are often overused for: take text or JSON, answer a fixed set of typed questions, and return labels, scores and probabilities without generating prose. The Python package exposes choice, ordinal-score and boolean-probability primitives, plus presets for model routing, prompt guardrails,…",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 123,
      "text": "Apache-2.0 local decision engine for a narrow job generative models are often overused for: take text or JSON, answer a fixed set of typed questions, and return labels, scores and probabilities without generating prose. The Python package exposes choice, ordinal-score and boolean-probability primitives, plus presets for model routing, prompt guardrails, moderation and support-ticket triage. Three open checkpoints cover English, multilingual input and the project's task-tuned workflows."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 249,
      "text": "or JSON, answer a fixed set of typed questions, and return labels, scores and probabilities without generating prose. The Python package exposes choice, ordinal-score and boolean-probability primitives, plus presets for model routing, prompt guardrails, moderation and support-ticket triage. Three open checkpoints cover English, multilingual input and the project's task-tuned workflows.\n\n- Apache-2.0, Python package, open Hugging Face weights, three checkpoints and local inference independently verified from the repo and model card on 2026-09-19 (github.com/NandhaKishorM/laya, ~846 stars, pushed 2026-09-19; convaiinnovations/laya, ~406 Hugging Face likes).\n- Surfaced in both lanes: the 2026-09-19 discovery pull carried the launch at 567 HN points, and the viral-X pull carried it as the open alternative to TypeSafe Jev.\n- The 33 ms single-question latency, benchmark scores and Jev comparisons are the maker's published T4 results. They were not independently rerun for this registry."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 241,
      "text": "lanes: the 2026-09-19 discovery pull carried the launch at 567 HN points, and the viral-X pull carried it as the open alternative to TypeSafe Jev. - The 33 ms single-question latency, benchmark scores and Jev comparisons are the maker's published T4 results. They were not independently rerun for this registry.\n\nSupport routing, lead classification, churn flags and prompt screening are decision problems before they are writing problems. Laya gives those steps a local, inspectable probability instead of paying a large model to write a sentence that another rule has to parse. That makes it useful ahead of a CRM, support queue or agent tool call where low confidence should hand the case to a person. The honest read is in the project's own limitations: use the task-tuned checkpoint for its advertised workflows, fit calibration on your data, and do not treat a confident score as proof when the input or label space falls outside what the model handles well."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/laya/index.md",
    "html": "https://gtmstacker.com/registry/tool/laya/",
    "json": "https://gtmstacker.com/registry/tool/laya/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/laya/server.json"
  },
  "jsonld": {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "WebSite",
        "@id": "https://gtmstacker.com/#website",
        "url": "https://gtmstacker.com/",
        "name": "GTM Stacker Agent Registry",
        "description": "A daily-updated, agent-native registry of open-source tool discoveries, tool updates, and curated news for the go-to-market / RevOps engineering niche. Machine-readable first: agents can discover, parse, page, and delta-sync it without scraping HTML.",
        "inLanguage": "en",
        "publisher": {
          "@id": "https://gtmstacker.com/#organization"
        }
      },
      {
        "@type": "Organization",
        "@id": "https://gtmstacker.com/#organization",
        "name": "GTM Stacker",
        "url": "https://gtmstacker.com",
        "description": "The growth-systems practice of Theo Popov: AI-native enrichment, outbound, content engines and internal tooling for startups and venture programs. Its agent-native media property, the GTM Stacker Agent Registry, maintains a daily-updated catalog of open-source go-to-market and RevOps tools that both people and AI engines can discover, compare, and cite.",
        "foundingDate": "2024-08",
        "knowsAbout": [
          "go-to-market engineering",
          "RevOps",
          "sales automation",
          "marketing operations",
          "open-source software",
          "AI agents"
        ],
        "founder": {
          "@type": "Person",
          "@id": "https://gtmstacker.com/#founder",
          "name": "Theo Popov",
          "jobTitle": "Growth Operations & GTM Systems",
          "url": "https://gtmstacker.com/about/",
          "sameAs": [
            "https://www.linkedin.com/in/theo-popov",
            "https://x.com/Theo_Popov",
            "https://github.com/theopopov"
          ],
          "worksFor": {
            "@id": "https://gtmstacker.com/#organization"
          }
        },
        "sameAs": [
          "https://www.linkedin.com/company/gtmstacker",
          "https://www.youtube.com/@gtmstacker",
          "https://www.instagram.com/gtmstacker/",
          "https://www.tiktok.com/@gtmstacker"
        ],
        "mainEntityOfPage": "https://gtmstacker.com/registry/about/"
      },
      {
        "@type": "SoftwareApplication",
        "@id": "https://gtmstacker.com/registry/tool/laya/#software",
        "name": "Laya",
        "identifier": "io.github.NandhaKishorM/laya",
        "description": "Apache-2.0 local decision engine (Python, open weights) for classifying and scoring text without generating prose. It returns typed choices, ordinal scores and boolean probabilities in one forward pass, with presets for routing, guardrails, moderation and support triage. Three checkpoints cover English, multilingual and task-tuned work. The project reports 33 ms on a T4, but also discloses weak zero-shot performance on the base model and the need for domain calibration.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/laya/",
        "datePublished": "2026-09-19T00:00:00Z",
        "dateModified": "2026-09-19T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "license": "https://spdx.org/licenses/Apache-2.0.html",
        "codeRepository": "https://github.com/NandhaKishorM/laya",
        "keywords": "ai-infrastructure, marketing-ops, chat-helpdesk, classification, model-routing, support-triage, self-hostable",
        "author": {
          "@type": "Organization",
          "name": "NandhaKishorM",
          "url": "https://github.com/NandhaKishorM",
          "sameAs": [
            "https://github.com/NandhaKishorM/laya"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        }
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/laya/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "AI Infrastructure",
            "item": "https://gtmstacker.com/registry/category/ai-infrastructure/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "Laya",
            "item": "https://gtmstacker.com/registry/tool/laya/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "io.github.NandhaKishorM/laya",
    "repository": {
      "url": "https://github.com/NandhaKishorM/laya",
      "source": "github"
    }
  }
}