Vibe Remote
Code from your phone — AI agents in your chat app
What it does
Vibe Remote turns Slack, Discord, Wechat and Lark into a remote control for AI agents. Type a message in chat → Claude Code, OpenCode, or Codex reads your codebase, writes code, and streams results back in real-time. Each thread is an isolated session — run parallel tasks across channels. Local-first. Your code never leaves your machine. One-command install with a guided setup wizard. Open source, MIT licensed. Code from your phone. No laptop. No IDE. Just vibes.
Does the same job
all alternatives →
- VRVibe Remote – Code from your bed or the park with Claude Code/CodexMar 2026 · vibe-remote.com · ▲7
I built Vibe Remote because I wanted to code from my bed or the park without lugging a laptop around. With tools like Claude Code, Codex, and Gemini-cli, we don't need a full IDE for every task anymore. Vibe Remote turns your phone into a powerful remote console. Why it’s more than just a chat: * AI Agent Hub: Zero-config support for Claude Code, Codex, and OpenCode. * Built-in Web Preview: View your localhost services directly inside the app. Essential for UI debugging. * Full Session Management: Start a task on your Mac, grab your phone, and monitor progress from a cafe. * Dev Ops: Manage…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
