Urgent.News

What's breaking now, across thousands of outlets.

AI

How to run Claude Code and Codex together on one server

install 5dive on a linux server, sign in once to your claude plan and once to your chatgpt plan, then create agents on each. they run as separate linux services, share one task list and can check each other's work. 5dive is open source (MIT) and free to self-host. i run 13 agents that way on one 4-core server: 12 on claude code, 1 on codex. the codex one is our copywriter. set it up curl -fsSL…

To run Claude Code and Codex simultaneously on a single server, follow these steps. First, install 5dive on a Linux server. Then, sign in once to your Claude Code plan and once to your Codex plan. Create separate agents on each plan, allowing them to run as independent Linux services and share a single task list. They can also check each other's work.

5dive is an open-source project (MIT license) that enables self-hosting of these services. You can deploy up to 13 agents on a 4-core server using this setup. The Codex agent can be assigned to handle copywriting tasks, while the Claude Code agent manages other responsibilities. Set up the agents using the command line: `curl -fsSL https://install.5dive.ai | sudo bash`.

Each agent runs as its own Linux user with customizable permissions. Agents only begin working when tasks are assigned to them. The system utilizes one shared task list, with agents switching between Claude Code and Codex as needed. You can move an agent between plans, and all tasks and memory are preserved.

To monitor usage, run `sudo 5dive usage` to see how your plans' limits are being utilized. The free web app is available at 5dive.app/self-host. Additionally, 5dive supports other teams running Hermes, OpenClaw, OpenCode, Pi, or Claude Code on alternative models. Start with a minimal 1 GB server, and explore more information at 5dive.ai/compare/claude-code-and-codex-together or visit the GitHub repository: github.com/5dive-ai/5dive.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at dev.to →

More in AI

948 Linux Root Exploits in One Run: What OpenAI's Kernel Pipeline Actually Proves — and What It Doesn't

OpenAI's November 4 research post, "A thousand fewer paths to root," reports a striking result: a prototype pipeline powered by an upcoming cyber model scanned the Linux kernel in mid-October 2026 and…

  • OpenAI published research on 948 Linux kernel LPE exploits with patches.
  • Pipeline involved five stages with human review at each step.
  • 948 unique LPEs were verified as local privilege escalations requiring low-privileged access.

More from Thursday 5 November →