Tiny offline tool-calling model for devices
A 14 MB tool-calling model designed for phones, wearables, and other constrained devices, with offline operation, fine-tuning, and confidence-based escalation.
From ManuAGI - AutoGPT Tutorials — Trending Open-Source GitHub Projects : Kaneo, Rome, Paseo, Proliferate & Screendrop #288 at 04:34
Problem: Large models do not fit on small devices, while structured tool use is still needed.
For: On-device AI developers.
Products from this video
CesiumJS Claude Code Claude Code Plugins Directory Cloudflare D1 Cloudflare R2 Cloudflare Workers Docker Compose Doop Doop ego lite Electron Git God's Eye View Google 3D Tiles hayamimi (早耳) Kaneo Kubernetes LatticeDB learn LiveKit LiveKit Agents MAX Framework Model Context Protocol (MCP) Modular Platform Mojo Dialer Munder Difflin Munder Difflin Needle 2 OCR It OpenAI Realtime API OpenAI Realtime API Paseo Paseo Proliferate Proliferate Python Rome Rome Screendrop SwarmForge Tailcat Tailscale Tesseract OCR vphone-cli