Ollaya: run decision models locally, TypeSafe-compatible
Ollama-style local runtime for open decision models: typed, calibrated answers in milliseconds behind a TypeSafe-compatible API.
Why it matters
The first open local runtime for decision models; TypeSafe's official Python SDK works unchanged against a local server, and laya answers a five-question request in ~10ms on an RTX 4090.
What you could build with it
Zero-cost local decision layer for the X DM triage flow: point the TypeSafe SDK at localhost and gate every draft send on a local calibrated verdict, keeping the OpenRouter budget untouched.
Does it hold up?
Launched Sept 25, 2026 to a 480+ point HN front page; no independent third-party builds or integrations found yet. Too early to judge real-world usability beyond the vendor's latency claims.
Built with Ollaya
- Ollaya - Ollama for open-source, Jev-style decision models (WeSearch summary)wesearch · Summary of the HN front-page story tracking Ollaya's launch and its TypeSafe-compatible local decision models.
- LAXIMA AI Signal brief: Ollaya (HN, 425 points)laxima · Curated HN signal brief noting Ollaya surfaced with 425+ points as an open-source local tool for TypeSafe-compatible decision models.
Learn more
First spotted on article: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.