{"slug":"unsloth-desktop","name":"Unsloth Desktop","summary":"Desktop app that downloads and serves local decision models such as Laya or Clef on macOS, Windows, and Linux (manual install also covers WSL). It turns text into structured yes/no, choice, or score decisions with probabilities, and can expose them through a TypeSafe-compatible J","publisher":"Unsloth","homepage":"https://unsloth.ai/docs/models/decision-laya","kind":"runtime","hasApi":true,"hasMcp":false,"costRange":"unknown","costNotes":"Pricing is not stated. The page only describes downloading the Unsloth Desktop app and local model weights (Multilingual 678 MB, English and Typed decisions 846 MB) with stated RAM needs. No license, subscription, or usage price is given.","functions":["classify","code","index","memory","route"],"slices":[{"functionId":"classify","label":"Local Laya decision requests","note":"Send text plus up to 64 questions. noul returns the probability of yes; choice returns the most likely option and a probability per option (up to 255 options); score places text on a scale from 0 (up to 10 levels). Choice and score also return confidence. Stated variants: Multilingual (default, 100+ languages, 1024 token context), English (512 token context), and Typed decisions.","cost":"Unknown"},{"functionId":"code","label":"code","note":"Inferred from executor","cost":"Unknown"},{"functionId":"index","label":"index","note":"Inferred from executor","cost":"Unknown"},{"functionId":"memory","label":"memory","note":"Inferred from executor","cost":"Unknown"},{"functionId":"route","label":"route","note":"Inferred from executor","cost":"Unknown"}],"interfaces":[{"kind":"http"}],"composabilityRationale":"The page states a local Decision API (Settings → API → Serve requests), access tokens or keyless localhost access for chat and inference, and pip install typesafe-sdk so existing Jev clients can point at the local server. Model ids include laya, default, jev-latest, laya-multilingual, laya-english, and laya-typed-decisions. MCP is not mentioned. Confidence uses a different formula than Jev, and choice options share a token budget that can trim labels past about 20 described options.","signals":[],"functionProbabilities":[{"functionId":"classify","value":0.8,"source":"https://unsloth.ai/docs/models/decision-laya","method":"lexical","observedAt":"2026-10-19T01:45:19.990Z"},{"functionId":"code","value":0.8,"source":"https://unsloth.ai/docs/models/decision-laya","method":"lexical","observedAt":"2026-10-19T01:45:19.990Z"},{"functionId":"index","value":0.8,"source":"https://unsloth.ai/docs/models/decision-laya","method":"lexical","observedAt":"2026-10-19T01:45:19.990Z"},{"functionId":"memory","value":0.8,"source":"https://unsloth.ai/docs/models/decision-laya","method":"lexical","observedAt":"2026-10-19T01:45:19.990Z"},{"functionId":"route","value":0.72,"source":"https://unsloth.ai/docs/models/decision-laya","method":"lexical","observedAt":"2026-10-19T01:45:19.990Z"}],"claimVerification":[{"key":"mcp","status":"unverified","asserted":"false","evidenceSource":"https://unsloth.ai/docs/models/decision-laya","method":"fallback"},{"key":"api","status":"unverified","asserted":"true","evidenceSource":"https://unsloth.ai/docs/models/decision-laya","method":"fallback"},{"key":"cost","status":"unverified","asserted":"unknown","evidenceSource":"https://unsloth.ai/docs/models/decision-laya","method":"fallback"},{"key":"license","status":"unverified","asserted":"","evidenceSource":"https://unsloth.ai/docs/models/decision-laya","method":"fallback"}],"tweets":[],"notes":[],"origin":"intake","createdAt":"2026-10-19T01:45:20.765Z","updatedAt":"2026-10-19T01:45:20.765Z","sources":[{"kind":"web","label":"executor","url":"https://unsloth.ai/docs/models/decision-laya","excerpt":"For the complete documentation index, see llms.txt. This page is also available as Markdown.\n\nRun and serve decision models like **Laya** or **Clef**, open Jev alternatives, on your local **Mac**, **Windows** and **Linux** device with Unslo","at":"2026-10-19T01:45:20.765Z"}],"recordId":"cmp_unsloth-desktop","claims":{"name":"Unsloth Desktop","summary":"Desktop app that downloads and serves local decision models such as Laya or Clef on macOS, Windows, and Linux (manual install also covers WSL). It turns text into structured yes/no, choice, or score decisions with probabilities, and can expose them through a TypeSafe-compatible J","kind":"runtime","publisher":"Unsloth","homepage":"https://unsloth.ai/docs/models/decision-laya","costRange":"unknown","costNotes":"Pricing is not stated. The page only describes downloading the Unsloth Desktop app and local model weights (Multilingual 678 MB, English and Typed decisions 846 MB) with stated RAM needs. No license, subscription, or usage price is given.","functions":["classify","code","index","memory","route"],"slices":[{"functionId":"classify","label":"Local Laya decision requests","note":"Send text plus up to 64 questions. noul returns the probability of yes; choice returns the most likely option and a probability per option (up to 255 options); score places text on a scale from 0 (up to 10 levels). Choice and score also return confidence. Stated variants: Multilingual (default, 100+ languages, 1024 token context), English (512 token context), and Typed decisions.","cost":"Unknown"},{"functionId":"code","label":"code","note":"Inferred from executor","cost":"Unknown"},{"functionId":"index","label":"index","note":"Inferred from executor","cost":"Unknown"},{"functionId":"memory","label":"memory","note":"Inferred from executor","cost":"Unknown"},{"functionId":"route","label":"route","note":"Inferred from executor","cost":"Unknown"}],"interfaces":[{"kind":"http"}],"composabilityRationale":"The page states a local Decision API (Settings → API → Serve requests), access tokens or keyless localhost access for chat and inference, and pip install typesafe-sdk so existing Jev clients can point at the local server. Model ids include laya, default, jev-latest, laya-multilingual, laya-english, and laya-typed-decisions. MCP is not mentioned. Confidence uses a different formula than Jev, and choice options share a token budget that can trim labels past about 20 described options."},"relations":[{"from":"unsloth-desktop","to":"e2b-vs-daytona-vs-blaxel-ai-sandbox-comparison","kind":"fills-same-slot-as","note":"Shared functions code, memory, route. Can fill the same function slot."},{"from":"unsloth-desktop","to":"agentmemory","kind":"fills-same-slot-as","note":"Shared functions code, memory. Can fill the same function slot."},{"from":"unsloth-desktop","to":"best-code-execution-sandbox-for-ai-agents-in-2026","kind":"fills-same-slot-as","note":"Shared functions code, memory, route. Can fill the same function slot."},{"from":"unsloth-desktop","to":"onyx","kind":"fills-same-slot-as","note":"Shared functions code, index, route. Can fill the same function slot."},{"from":"unsloth-desktop","to":"how-hopx-achieves-100ms-cold-starts","kind":"fills-same-slot-as","note":"Shared functions code, memory. Can fill the same function slot."},{"from":"unsloth-desktop","to":"pageindex","kind":"fills-same-slot-as","note":"Shared functions index, memory. Can fill the same function slot."},{"from":"unsloth-desktop","to":"best-stateful-sandboxes-for-code-execution-in-2026","kind":"fills-same-slot-as","note":"Shared functions code, memory. Can fill the same function slot."},{"from":"unsloth-desktop","to":"comparing-ai-agent-sandbox-platforms-e2b-modal-daytona-and-more","kind":"fills-same-slot-as","note":"Shared functions code, memory. Can fill the same function slot."}],"explain":{"score":6,"formula":"100 × sum(weight × value) over observed factors only. Unobserved factors are omitted, not zeroed.","factors":[{"id":"github_health","label":"GitHub health","weight":0.18,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"agent_use","label":"Agent use","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"human_notes","label":"Human notes","weight":0.14,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"composability","label":"Composability","weight":0.16,"why":"insufficient evidence","sources":[],"evidence":"insufficient"},{"id":"checklist","label":"Checklist","weight":0.1,"value":0.3333333333333333,"contribution":0.03333333333333333,"why":"No MCP surface is declared. An API is declared. Cost is unknown. 1 of 3 checklist fields are complete.","sources":[],"evidence":"observed"},{"id":"evidence_quality","label":"Evidence quality","weight":0.14,"value":0.18107144632819594,"contribution":0.025350002485947435,"why":"1 sources cover 1 evidence types. The latest dated evidence is 2026-10-19. Freshness is omitted unless observed as a signal.","sources":[{"kind":"web","label":"executor","url":"https://unsloth.ai/docs/models/decision-laya","excerpt":"For the complete documentation index, see llms.txt. This page is also available as Markdown.\n\nRun and serve decision models like **Laya** or **Clef**, open Jev alternatives, on your local **Mac**, **Windows** and **Linux** device with Unslo","at":"2026-10-19T01:45:20.765Z"}],"evidence":"observed"},{"id":"benchmark","label":"Benchmarks","weight":0.12,"why":"insufficient evidence","sources":[],"evidence":"insufficient"}],"missing":["GitHub health: insufficient evidence","Agent use: insufficient evidence","Human notes: insufficient evidence","Composability: insufficient evidence","Benchmarks: insufficient evidence"]},"score":6}