What do you want to do?
4 use cases
-
Run persistent agents on a headless server
Install OpenBot on a VPS or home server so agents keep running when your laptop is off.
- Openbot
- Software and DevOps
- Intermediate
View prompt
In the nightly-labs/openbot repo, install the always-on server on <target-host> following docs/self-hosted-server.md. Expected output: the result of `sudo openbot login` showing a completed sign-in and a list of agents reachable from the desktop app. Verify the sign-in finished before reporting success.
-
Split a coding task across Codex and Claude agents
Give each agent its own workspace and queue, then delegate parts of a task between them.
- Openbot
- Codex
- Claude Code
- Software and DevOps
- Intermediate
View prompt
In the nightly-labs/openbot repo, set up a Codex agent and a Claude agent in the desktop app, each with a separate workspace under <project-path>. Expected output: both agents listed with queued tasks and one agent-to-agent message sent. Verify that each agent's queue shows the task before reporting success.
-
Have an agent research and test sites in its own browser
Let a persistent agent open, inspect, and control the embedded browser for web research or QA.
- Openbot
- Software and DevOps
- Beginner
View prompt
In the nightly-labs/openbot repo, create an agent in the desktop app and ask it to open each URL in <url-list> in the embedded browser and report the page title and any visible errors. Expected output: a per-URL list of results in the agent's conversation. Verify that every URL was opened before reporting success.
-
Run an agent on a local model with Ollama or LM Studio
Connect an agent to a local model server so prompts stay on your machine.
- Openbot
- Software and DevOps
- Intermediate
View prompt
In the nightly-labs/openbot repo, connect the desktop app to the local model server at <endpoint-url> and create an agent that uses it. Expected output: one test reply from the agent in its conversation. Verify the reply came from the local server before reporting success.
How to use Openbot
- Check you have what it needs: A macOS 13+, Windows 10+, or x64/arm64 Linux AppImage machine, or an Ubuntu 24.04 host with systemd for the server; An account with at least one supported provider (Codex, Claude, Grok, OpenCode, Gemini, Cursor, or Cline), or a local model server such as Ollama or LM Studio; Willingness to run agents with danger-full-access and approvalPolicy never after the first-launch consent.
- Open nightly-labs/openbot on GitHub and read the README and license.
- Use an Ubuntu 24.04 VPS or home server that runs systemd, and open a terminal on it.
- Run
curl -fsSL https://raw.githubusercontent.com/nightly-labs/openbot/main/scripts/install-server.sh | sudo bash - Run
sudo openbot loginand enter the one-time email code. - Open the desktop app, the iPhone app, or Openbot.run/app and confirm the agents appear.
These steps come from our top use case, Run persistent agents on a headless server, which also has a copy-paste agent prompt.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeOpenbot alternatives · Best AI repos for Software and DevOps
About this repo
- Who it is forDevelopers and technical team leads who want several AI coding agents working on their own machines with shared queues and handoffs.
- Why it is hot
- LanguageTypeScript
- Sourcegithub.com/nightly-labs/openbot · Back to Hot repos
Requirements
- A macOS 13+, Windows 10+, or x64/arm64 Linux AppImage machine, or an Ubuntu 24.04 host with systemd for the server
- An account with at least one supported provider (Codex, Claude, Grok, OpenCode, Gemini, Cursor, or Cline), or a local model server such as Ollama or LM Studio
- Willingness to run agents with danger-full-access and approvalPolicy never after the first-launch consent
Maintain Openbot? Add the Featured on Deduped badge
Paste this into your README:
[](https://dedupedai.com/use-cases/nightly-labs-openbot/?ref=badge)
Questions about Openbot
What is Openbot?
OpenBot is a local-first desktop app and optional always-on server for running persistent AI coding and assistant agents, each with its own workspace, queue, and conversation. It is an open-source project on GitHub: https://github.com/nightly-labs/openbot.
Who is Openbot for?
Developers and technical team leads who want several AI coding agents working on their own machines with shared queues and handoffs.
What can I do with Openbot?
4 use cases so far, for example: Run persistent agents on a headless server; Split a coding task across Codex and Claude agents; Have an agent research and test sites in its own browser. Each has steps and a copy-paste agent prompt.
What do I need to run Openbot?
A macOS 13+, Windows 10+, or x64/arm64 Linux AppImage machine, or an Ubuntu 24.04 host with systemd for the server; An account with at least one supported provider (Codex, Claude, Grok, OpenCode, Gemini, Cursor, or Cline), or a local model server such as Ollama or LM Studio; Willingness to run agents with danger-full-access and approvalPolicy never after the first-launch consent.
What are alternatives to Openbot?
Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.
Is Openbot safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.