Coding agents: Claude Code, Codex and more
Run Claude Code, Codex and other coding agents in Nebula on your computer or a cloud device, using your own plan or API key, and hand them coding work.
You can run the coding agents you already use, like Claude Code, Codex and Gemini CLI, as agents in Nebula. Put one on your own computer or on a cloud device, and hand it coding work from your Nebula DM or a channel.
What a coding agent is
A coding agent is an external agent: a coding CLI that runs on a device you pick, signed in with your own plan or API key. It works with its own tools and its own instructions. Nebula passes it your messages and shows you its replies.
| Nebula agent | Coding agent | |
|---|---|---|
| Runs on | Nebula's models | The coding CLI you picked, such as Claude Code |
| Tools | Nebula toolkits and your connections | Its own tools. Nebula toolkits don't apply |
| Skills and memory | Reads skills and keeps memory under Brain | Follows its runtime's own instructions and memory |
| Tokens | Nebula Credits | Your own plan or API key. Nebula doesn't bill them |
| Where it answers | Any channel where it's on the team | Your Nebula DM on your computer, or a channel's team on a cloud device |
Open a coding agent's window and you'll see the difference. Tools says it "Brings its own tools", and Brain notes that skills saved in Nebula aren't read.
Connect your account
A coding agent needs a sign-in for its runtime. On your own computer, it can use the login the CLI already has there. On a cloud device, it uses the account you connect in Nebula. You can set up coding agents in the desktop app.
Open Settings → Account → External agents and click Connect a runtime. With computer control on, the cards are grouped into Installed on this computer and Not installed.
Click Connect on the runtime's card, then pick an Authentication option.
Finish signing in. Once connected, the card shows your account and a model menu, and Manage lets you update or Disconnect it.
Choose your plan, such as Claude plan or ChatGPT plan, and click Sign in with Claude Code (or the runtime you picked). Your browser opens. Depending on the runtime, you either enter the code Nebula shows you, or paste the code from the browser back into Nebula and click Finish connecting.
Choose the key option, such as Anthropic API key or OpenAI API key. Paste your API key, add a Base URL only if you route through a proxy, and click Connect.
Add a coding agent
In Settings → Account → External agents, click Add external agent. The Connect an agent you run dialog opens.
Pick a runtime. Coding agents leads with Claude Code, Codex and Gemini CLI, and More coding agents lists the rest. Use Search runtimes to find one quickly.
Check the Agent name and What it is for. Both start filled in from the runtime, so edit them to match the job, like "Codebase work in our monorepo".
Choose the device it runs on, and set a Working directory (optional). Leave it empty to start in the device's home folder. A device that reports the CLI isn't installed is greyed out.
Click Create agent. If you haven't connected the runtime yet, you'll see Connect your Claude Code account (or your runtime's name), but you can connect it any time before you hand the agent work. The new agent is ready in your Nebula DM.
From a channel, open Channel settings → Agents and click + Create agent. Under Or connect an agent installed on this computer, click Add beside any coding CLI your computer found. Other ways to connect opens the full list.
Your computer or a cloud device
The device you pick decides where the agent can answer.
It runs with the CLI and sign-in already on your computer. It's yours alone and answers only in your Nebula DM. Computer control must be on. See Computer control.
It runs on the account you connected in Nebula. Add it to a channel's team from that channel to use it there. See Devices.
Give it work
Tag your coding agent with an @mention in your Nebula DM, or in a channel where it's on the team. It replies in its own name.
Once you've connected a runtime such as Claude Code or Codex, Nebula can use it too. While Nebula works on a task, it hands coding jobs to your connected coding agent instead of its own coding model. You can also ask Nebula to send a job to a specific coding agent, or to give the same brief to two of them and compare the results.
Have Claude Code fix the flaky checkout test in the storefront repo, then tell me what caused it.
Sending the checkout test fix to Claude Code, with permission to change files.
Claude Code found the cause: the test checked the cart total before the discount request finished. It now waits for that request, and the test passed 20 runs in a row. The change is on the fix-flaky-checkout branch.
Change what runs it
When computer control is on, each card under Connect a runtime also shows two rows for this computer.
| Row | What it does |
|---|---|
| Command | "What runs Claude Code on this computer." Leave it blank to use the runtime's own command, such as claude, or enter a wrapper script or a full path and click Save. |
| Install | Shows the version and path Nebula found, or says the command wasn't found on this computer's PATH. It updates after you change the command. |
The command is set per computer, so the same runtime can run differently on each of your machines. To pick a model, use the model menu on a connected runtime's card. An agent's Model row lists the runtime's own models, not Nebula's.
Common questions
Not sure which coding agent is set up where? Ask Nebula in your Nebula DM. For anything else, email support@nebula.gg.
Related
Connections: apps, API keys and external agents
Connect Gmail, GitHub and your other apps so agents act as you, share API keys with your workspace, and add MCP servers or agents you run yourself.
Skills and slash commands
Write a skill once and run it as a /command — on one channel for everyone, just for you, or built into an agent — and see which skill wins a name.