BTS Chatter vs noni

Chatter - Your agents. Your tools. Your data. Chatter is the AI chat app we built for ourselves - because we wanted frontier-quality answers without handing our conversations to yet another data-hungry platform. Now it's yours too. Chatter runs on Ollama Cloud with zero data retention: your prompts and answers are processed, streamed back, and gone. Nothing stored server-side, nothing used for training. Just fast inference on powerful open models - and a native, lightweight app on iPhone, iPad, and Mac that stays out of your way. Private by design. No account, no sign-up, no login - enter your API key and start chatting. We collect nothing: no analytics, no tracking, no telemetry. Your chats, agents, and knowledge live on your devices and sync exclusively through your personal iCloud (Apple CloudKit), end-to-end within your own Apple ID. We couldn't read your data if we wanted to - and we don't want to. Build your own agents. Create assistants with their own personality, model, and toolset - a coding expert, a research companion, a home-automation operator. Each agent is exactly as capable (and as locked-down) as you decide. Give them tools with MCP. Connect any Model Context Protocol server - self-hosted on your LAN, over Tailscale, or anywhere else. Your agents can query your databases, control your smart home, or reach your internal APIs. Your infrastructure stays yours. Give them knowledge. Attach curated knowledge bases to any agent - import PDFs or Markdown, and your agent reads exactly the documents it needs, when it needs them. Watch them grow. Agents remember what matters: they keep their own notes about you and your projects across chats, and they can even write down reusable skills - procedures you teach them once and they follow forever. You stay in control: everything they learn is visible, editable, and deletable. Everywhere you are. One app for iOS and macOS, with your agents, chats, and knowledge synced privately through iCloud. No subscription. No middleman. No tracking. Chatter is a native client for your own Ollama Cloud account - bring your API key, and own your AI. **Requires an Ollama Cloud API key (ollama.com). Chatter connects directly to Ollama Cloud and to MCP servers you configure; we run no servers of our own.**

noni is a team of small AI models that live on your device. Instead of one giant model in the cloud, noni orchestrates several small open-weight language models locally: a tiny router reads each request and hands it to the right specialist - general chat, coding, or writing. Nothing you type ever leaves your device. PRIVATE BY ARCHITECTURE • zero data collection - no account, no analytics, no tracking • conversations are stored only on your device • the network is used for one thing: downloading model weights from Hugging Face • after a model is downloaded, it works in airplane mode A TEAM, NOT A SINGLE MODEL • auto - a 0.6B router classifies each request and picks the specialist • solo - pin any downloaded model and talk to it directly • relay - pipelines like draft → polish, one model refining another's work • council - two models answer, a third merges the best of both BUILT TO RUN ON YOUR DEVICE • Apple's MLX framework with 4-bit quantized models and streaming replies • markdown rendering with copyable code cards • background, resumable model downloads • automatic conversation titles, edit & resend, regenerate • add any public model from Hugging Face by pasting a link • a strict black-and-white design: no clutter, no color, no distractions MODELS & SIZES (download only what you need) • qwen3 0.6b - router and quick chat, ~350 MB • llama 3.2 1b - everyday general model, ~710 MB • gemma 3 1b - rewriting and summarizing, ~770 MB • qwen2.5 coder 1.5b - writes and explains code, ~880 MB • qwen3 1.7b - stronger generalist for recent devices, ~980 MB • llama 3.2 3b - the most capable, for high-memory devices, ~1.8 GB The starter pack (router + general model) is about 1.1 GB. Models are free, open-weight, and hosted on Hugging Face. HONEST EXPECTATIONS Small local models are fast, private, and surprisingly capable for everyday questions, quick code snippets, and rewrites - but they are not cloud giants. Expect roughly 10-30 tokens per second on recent devices, and occasional mistakes. That is the trade for total privacy, zero cost, and offline use. Requires iOS 17 or later. On older or lower-memory devices, stick to the smaller models; the library labels which models want a high-memory device. Built with Llama. Qwen models are Apache-2.0 by Alibaba Cloud; Gemma is provided under Google's Gemma Terms of Use; inference runs on Apple's open-source MLX.