Happier vs LM Pocket

Happier is an open-source, end-to-end encrypted companion app for AI coding agents: Claude Code, Codex, OpenCode, Cursor, Pi, Grok, Gemini, Copilot, Qwen, Kimi, Kilo, Kiro, Auggie. Run sessions on your computer, and continue them from your phone. Use our desktop app or web app, and truly start working from anywhere. YOUR EXISTING SESSIONS? ALREADY THERE. Open any Claude Code, Codex or OpenCode session running on your computer — live, from your phone. Nothing to migrate, nothing to learn. APPROVE FROM ANYWHERE Your agent asks to run a command and you get a push notification with Allow and Deny on it. Sessions waiting on a decision rise to a "Needs attention" group at the top of your list; everything still running gathers under "Working". REVIEW THE DIFF. SEND NOTES TO YOUR AGENTS. Browse every line your agent changed. Mark the exact lines you want addressed, choose which notes to send, and hand them straight back — same session, or a new one. EDITOR. GIT. TERMINAL. ONE TAP AWAY. Chat, files, Git and a live terminal, each its own tab. Open a file to read or edit it, review the diff, manage branches and open a pull request. YOU LOVE THE TERMINAL? WE DO TOO. If you want, you can keep running Claude Code, Codex or OpenCode in their native TUI. Happier mirrors them to every device, so you can follow along, send messages and approve permissions from anywhere — and switch between the terminal and Happier whenever you like. A COLLEAGUE YOU CAN TALK TO The voice assistant watches every running session. Brainstorm the next change, approve a permission or send a message, without picking up the phone. YOUR SESSIONS WORK AS A TEAM A session can start another session, send it messages and read its transcript — so a Claude session and a Codex session can split the work between them. Each one still runs its own subagents, on whichever backend you choose. USE THE SUBSCRIPTIONS YOU ALREADY PAY FOR Happier reuses the subscriptions and logins your existing CLIs already use — Claude, Codex, Cursor, Gemini, OpenCode. No new bill, no double billing, and Happier sells no AI of its own. POOL YOUR ACCOUNTS. KEEP THE SESSION GOING. Link accounts you own into a pool and watch usage and quota resets for every one of them in the app. Nothing switches until you build a pool — once you have, Claude Code and Codex sessions can change account without stopping, moving to whichever member has the most quota left, at most once a turn and never past a reset time the provider has published. OPEN SOURCE. END-TO-END ENCRYPTED. Your messages, prompts and session content are encrypted on your device before they reach a server: AES-256-GCM under a key drawn for that one session, sealed to an account key that is created on a device and never leaves your devices. The relay stores ciphertext and has nothing to open it with. Put the relay on your own hardware with one command — happier relay host install — or reach your computer over Tailscale and use no relay at all. FREE, AND MIT LICENSED The CLI, the mobile apps, the desktop app, the web app and the relay. No seat count, no trial, no feature gate. github.com/happier-dev/happier HOW TO START 1. On your computer: curl -fsSL https://happier.dev/install | bash (Windows: iwr https://happier.dev/install.ps1 -useb | iex) 2. Scan the QR code your terminal prints, with this app. 3. Start a session from the app, or run "happier claude" or "happier codex" in your terminal. REQUIRES A COMPUTER Happier is the client for agents running somewhere you control. It does not run an agent in the cloud, and your repository is never copied to us: the agent reads and writes files on the computer it runs on, and that computer stays the only full copy. Not affiliated with, or endorsed by, Anthropic, Google, GitHub or Cursor.

Discover, download, and run open-source AI models directly on your device. No cloud. No subscription. No data leaves your device. LM Pocket brings the power of local AI models to your device. Browse thousands of GGUF models on Hugging Face, download them over WiFi, and chat with them entirely on-device. COMPLETELY PRIVATE Every conversation stays on your device. No server, no API key, no account required. Your prompts and responses never leave the device. DISCOVER MODELS Browse Hugging Face Hub for quantized GGUF models. Filter by size, quantization level, and popularity. See compatibility badges that tell you which models will run well on your device before downloading. CHAT WITH AI Stream token-by-token responses with full Markdown rendering. Manage multiple conversations. Adjust temperature, top-p, top-k, context length, and more. Supports ChatML, Llama, Mistral, Phi, Gemma, and other prompt formats automatically. LOCAL API SERVER Run an OpenAI-compatible HTTP server on your device. Expose /v1/chat/completions, /v1/models, and /v1/embeddings endpoints on your local network. Connect any app that supports the OpenAI API format. MANAGE YOUR LIBRARY Track installed models with storage usage. Import GGUF files from the Files app. Load and unload models with one tap. Monitor real-time performance: tokens per second, memory usage, and thermal state. BUILT FOR POWER USERS - GPU acceleration for fast inference - Background downloads with pause and resume - Hardware-aware model recommendations - Chat template auto-detection - Conversation export as JSON or Markdown - JSON mode with grammar-constrained output - Embeddings generation 100% FREE No subscriptions, no in-app purchases, no ads. Open-source AI should be accessible to everyone. SUPPORTED MODELS Run any GGUF-quantized model: Llama, Mistral, Phi, Gemma, CodeLlama, DeepSeek, Qwen, and thousands more from Hugging Face Hub. Model performance depends on device RAM and model size. Terms of Service: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/