HelloAgent vs Local LLM runner

HelloAgent is an inbox for the personal AI agents you build. Build a small AI helper for yourself — a research assistant, a coding tutor, a journal companion, a recipe ideator — give it a handle, and chat with it from your phone or the web. Your agents, your handle, your inbox. — Build your own agent with the open-source SDK in Python or TypeScript. Pick your model — any LLM API or local runtime. Pick your tools. Pick your prompt. The agent runs wherever you want — on your laptop, a VPS, a Raspberry Pi. — Talk to it from anywhere. The HelloAgent app is one inbox for every agent you've built, with conversations that sync across iOS and the web client and survive the agent being offline. — Sign in with Apple, Google, or email + password. — Quiet, paper-textured design that takes the visual screaming out of chat. Optimised for long-form work, code blocks, and math. For builders: — Open-source SDK in Python and TypeScript — Streaming responses, tool calls, and capability declarations — Per-user OAuth-scoped tokens for personal-agent links — MIT licensed throughout — relay, SDK, and clients Learn more at helloagent.cc.

Run LLM on your iPhone, 100% local, no network (Network needed once to download a model) Models: • Qwen2.5 0.5B Instruct — ~0.4 GB (4 GB RAM) • Llama 3.2 1B Instruct — ~0.8 GB (4 GB RAM) • Qwen2.5 1.5B Instruct — ~0.9 GB (4 GB RAM) • Llama 3.2 3B Instruct — ~1.9 GB (6 GB RAM) • Qwen3 4B Instruct 2507 — ~2.5 GB (6 GB RAM) • Qwen2.5 7B Instruct — ~4.4 GB (8 GB RAM) Also: • Add your own GGUF (for example, from Hugging Face) • Auto-estimated max context from GPU memory; you can change it Requires iOS 18 or later. Tested on iPhone 11, 14 Pro, 15 Pro with iOS 26. Qwen models © Alibaba Cloud. Licensed under Apache License 2.0. Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Built with Llama. On-device inference uses llama.cpp (MIT License).