What do you want to do?
5 use cases
-
Run a local agent control plane and worker
Start Postgres, the control plane, the console and a worker on one machine to test agent task runs.
- REPO
wemux-ai/wemux - Software and DevOps
- Intermediate
View prompt
In the wemux repo at <repo-path>, follow the Quick start (self-hosted) steps to start infrastructure, server, client and worker. Report the console URL and confirm the worker shows as paired in the console.
- REPO
-
Add a worker on a second Mac or Linux machine
Install and pair a remote worker using the command generated in the console's Add Executor dialog.
- REPO
wemux-ai/wemux - Software and DevOps
- Intermediate
View prompt
Using the wemux console at <control-plane-url>, generate an Add Executor install command and run it on <worker-host>. Report whether the worker registers and appears under Execution.
- REPO
-
Deploy your own Wemux instance on Railway
Provision the control plane, Postgres and a bucket on Railway from the repo's infrastructure-as-code file.
- REPO
wemux-ai/wemux - Software and DevOps
- Advanced
View prompt
In the wemux repo at <repo-path>, deploy the control plane to Railway with the documented commands. Report the public HTTPS origin and confirm that /api/ready returns a healthy response.
- REPO
-
Delegate coding tasks to agents on your own workers
Describe a coding task in the main chat and have an agent run it in an isolated worktree for review.
- REPO
wemux-ai/wemux - Claude Code
- Codex
- Software and DevOps
- Intermediate
View prompt
Using the Wemux console at <control-plane-url>, create a task in workspace <workspace-name> asking an agent to <task-description>. Report the worker that ran it, the diff summary, and confirm nothing merged before approval.
- REPO
-
Create agent tasks from Feishu, Slack or DingTalk
Send a request from a team chat channel so the main agent turns it into a task for a worker.
- REPO
wemux-ai/wemux - Software and DevOps
- Advanced
View prompt
Send the request '<task-description>' through the connected <channel-name> integration in Wemux. Verify that a matching task appears in workspace <workspace-name> and report which worker received it.
- REPO
Quick start with Wemux
- Check you have what it needs: Node.js 20+; pnpm 10+; Docker (for Postgres).
- Open wemux-ai/wemux on GitHub and read the README and license.
- Clone the repo:
git clone https://github.com/wemux-ai/wemux.git, thencd wemuxand runpnpm install. - Start infrastructure with
pnpm dev:infra:up. - Copy the env template with
cp .env.development.local.example .env.development.localand set DATABASE_URL and OBJECT_STORAGE_* to match your setup. - Run
pnpm dev:server(API on :8989) andpnpm dev:client(web console) in separate terminals.
These steps come from our top use case, Run a local agent control plane and worker, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for wemux-ai/wemux
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forEngineering teams and solo developers who want AI agents to do coding tasks on their own machines with their own model keys.
- Why it is hot166 stars, launched 62 days ago
- LanguageTypeScript
- Sourcegithub.com/wemux-ai/wemux · Back to Hot repos
Requirements
- Node.js 20+
- pnpm 10+
- Docker (for Postgres)
- Git
- Your own model keys for OpenCode, Claude Code or Codex on the worker
Add this badge to your README
Maintain Wemux? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/wemux-ai-wemux/?utm_source=github&utm_medium=badge&utm_campaign=wemux-ai-wemux)
HTML
<a href="https://dedupedai.com/use-cases/wemux-ai-wemux/?utm_source=github&utm_medium=badge&utm_campaign=wemux-ai-wemux"><img src="https://dedupedai.com/badge/wemux-ai/wemux.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Wemux
What is Wemux?
Wemux is a self-hostable, Apache-2.0 platform that orchestrates AI agents to run coding work in isolated Git worktrees on worker machines you control. It is an open-source project on GitHub: https://github.com/wemux-ai/wemux.
How do I use Wemux?
Clone the repo: git clone https://github.com/wemux-ai/wemux.git, then cd wemux and run pnpm install; then start infrastructure with pnpm dev:infra:up; copy the env template with cp .env.development.local.example .env.development.local and set DATABASE_URL and OBJECT_STORAGE_* to match your setup. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Wemux for?
Engineering teams and solo developers who want AI agents to do coding tasks on their own machines with their own model keys.
What can I do with Wemux?
5 use cases so far, for example: Run a local agent control plane and worker; Add a worker on a second Mac or Linux machine; Deploy your own Wemux instance on Railway. Each has steps and a copy-paste agent prompt.
What do I need to run Wemux?
Node.js 20+; pnpm 10+; Docker (for Postgres); Git.
What are alternatives to Wemux?
Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.
Is Wemux 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.