Dev builds fully local AI todo system with three LiquidAI small models
helloiamleonie · x · 2026-10-18
Developer h14h showcased a fully local AI-powered todo system built by combining three small LiquidAI models, each handling a distinct role:
- D1-3B: action routing (deciding whether to create a new task or edit an existing one)
- LFM-2.5-24B-A2B: synthesizing transcription blobs into titles, descriptions, and deadlines
- LFM-2.5-Embedding-350M: semantic lookups over existing tasks
The demo is a practical blueprint for replacing cloud LLMs with a pipeline of small specialized local models for personal assistant workflows.
More from coding & agent
- Google's Deep Review Tore a 35-Page Benchmark Spec Apart Like a Hostile NeurIPS Chair — ChrisUniverse · 2026-10-18
- Google's Deep Review tore a 35-page benchmark spec apart, finding 36 flaws — ChrisUniverse · 2026-10-18
- Dev open-sources an X network map tool with a Grok agent prompt to collect data — jacob_posel · 2026-10-18
- Serverless, explained with a pizza shop and ghost kitchen analogy — thisiskp_ · 2026-10-18
- Pydantic AI CodeMode speculatively runs tools mid-generation, cutting 3 lookups from 8.7s to 4.7s — samuelcolvin · 2026-10-18
- 18 AI engineering concepts, from RAG variants to LoRA/QLoRA, mapped to open-source repos — MaryamMiradi · 2026-10-18