Omnara: Run Claude Code and Codex from Anywhere

Omnara is a web and mobile agentic IDE developed to allow seamless operation and interaction with Claude Code and Codex sessions from both desktop and mobile environments. It enables developers to run these sessions on their own machines and keep them accessible through a mobile and web GUI, offering flexibility when away from the desk.
The core innovation with Omnara lies in its ability to transition from local machines to a hosted remote sandbox when your device goes offline. The agent's conversation state is preserved on the server, and optional cloud syncing of working code is available. This feature utilizes git commits to maintain the state of the code base, allowing the session to continue smoothly upon shifting between local and cloud environments. Moreover, Omnara offers a voice agent for hands-free interaction, enhancing its utility while in motion.
The implementation involves a headless daemon on the user's machine, maintaining an outbound WebSocket connection with Omnara's server, facilitating uninterrupted communication between local and remote sessions. This setup obviates the need for exposed ports or SSH access, enhancing security and simplicity. Users can begin by executing the following command to install Omnara:
curl -fsSL https://omnara.com/install/install.sh | bashAfter installation, running omnara inside any git repository starts a headless Claude Code or Codex session linked to the Omnara web and mobile apps. The platform is available for free for up to 10 agent sessions monthly, with a $20/month subscription for unlimited sessions.
📖 Read the full source: HN AI Agents
👀 See Also

Echo-TTS Ported to Apple Silicon with MLX for Native TTS with Voice Cloning
Echo-TTS, a 2.4B parameter diffusion text-to-speech model with voice cloning, has been ported from CUDA to run natively on Apple M-series silicon using MLX. On a base 16GB M4 Mac mini, a 5-second voice clone takes about 10 seconds to generate, while 30-second clones take about 60 seconds.

BotCost.dev: Free Analyzer to See How Much AI Bots Cost Your Site
BotCost.dev is a free tool that analyzes your server logs against 18 known AI bot fingerprints (GPTBot, ClaudeBot, Perplexity, etc.) and estimates monthly bandwidth cost — no upload required, runs in-browser.

OpenClaw Setup on Ubuntu UTM VM with LLM API and Ollama Access
A user successfully configured OpenClaw in a sandboxed Ubuntu VM on an M3 Mac, with access to both local Ollama on macOS and external LLM APIs like Gemini, Claude, and DeepSeek. Sample configuration files and troubleshooting notes are available on GitHub.

Giving Claude a Local LLM as an Assistant via MCP on Mac
A developer connects Claude to a local Qwen 2.5 Coder 14B via Ollama and MCP, creating a no-cost assistant for delegating tasks like text processing and handling large files.