Sencha vs OH HAI

A native LLM client for on-device inference, LLM APIs, and self-hosted servers, built around a minimal, responsive interface. Download a supported model and chat offline without an API key or account. Or connect OpenRouter, direct providers, and compatible endpoints using your own credentials. On-Device Models • Download models from the built-in catalog, including Gemma 4, Qwen 3.5, Bonsai, and LFM 2.5 • Choose model sizes and quantization options to suit your device • Configure context window, reply length, and image detail where supported • Use streaming, thinking traces, image attachments, and web tools with compatible models • Reduce reprocessing of earlier messages with on-disk prompt caching Model capabilities and performance depend on the selected model and available device memory. Connections and Models • Connect OpenRouter, OpenCode, and direct providers • Add OpenAI- or Anthropic-compatible endpoints, including self-hosted runtimes such as Ollama and LM Studio • Use Chat Completions, Responses API, or Messages API • Choose an on-device or connected model per chat • Browse model catalogs and inspect context size, output limits, pricing, and capabilities where available • Configure reasoning effort, prompt caching, routing, and model tools where supported Web Search and Fetch • Use the included free web search via Markdown.new • Or configure Brave Search, Tavily, Exa, Serper, SerpApi, Parallel, or Keenable • Choose search-depth presets for Exa and Tavily • Fetch pages on device or through Markdown.new or Firecrawl • Configure fetch providers and fallbacks independently Files and Output • Attach photos, documents, and PDFs • Send PDFs natively, extract embedded text, run on-device OCR, or render pages as images • Read responses with formatted Markdown, code, mathematical formulas, and tables • Copy generated tables as a table, Markdown, or a complete image Voice Input • Use Apple Speech for on-device dictation • Download local transcription models • Connect API-based transcription providers The app is free, with no ads or app subscription. On-device models require no provider account or API key. Connected services are subject to their own pricing, limits, and data policies.

OH HAI is the universal inbox for your AI agent fleet. You cannot babysit agents that run around the clock across many projects. Three things break: agents sit blocked for hours waiting on a decision, manual tasks get buried in logs, and nobody has a high-level view of what shipped. OH HAI fixes all three. Every message from an agent is one of three types, easy to scan and quick to resolve: • A decision. The agent needs you to approve, pick an option, or supply a value. Answer in a tap and the agent continues. • A manual action. The agent needs you to do something it cannot: rotate a key, flip a setting, run a step. Mark it done and the agent learns. • An FYI or digest. Status, heads-ups, and a daily roll-up of what every agent did across every project. And you can reach back. Send a directive to any agent from the inbox. AGENTS TALK TO EACH OTHER TOO Each agent run opens a short-lived session with its own address. Agents can ask, task, and notify one another through the same inbox, across vendors and runtimes. A Claude Code session can hand work to a Codex or Cursor run, and you see the whole thread. You choose which agents may talk to each other. TRIAGE FROM ANYWHERE Push notifications for the things that need you. Snooze, archive, and search. Same inbox as the web. THE EXECUTIVE SUMMARY, WRITTEN BY YOUR FLEET Every day, or on demand, OH HAI rolls up what shipped, what is in flight, and the short list of what still needs you. WORKS WITH ANY AGENT, ANY VENDOR Connect agents three ways: hand your agent a setup prompt, install the CLI where your agents run, or add the hosted MCP server to the client you already use. Works with Claude Code, Codex, Cursor, and any runtime that has a shell or speaks MCP. OH HAI is the human side of the open MA2H protocol. Sign in with Apple, Google, or email. Free during open beta. Privacy policy: https://ohhai.app/privacy Terms: https://ohhai.app/terms