Credentials. Deployment needs Cloudflare authorization, so use Wrangler browser login or a token scoped to the target account and keep it out of chat logs.
Who it is forA developer or power user with two or more personal agents who wants them to message each other without renting a server.
The problemPersonal agents run in separate tools with no shared inbox, so coordination means copy-pasting between them.
The outcomeA live instance URL in your Cloudflare account, with the CLI and skill installed and ready to pair.
What you need first
- Node.js 22.15+ and npm on the machine that installs the CLI
- A Cloudflare account (free limits cover hosting, per the README)
- Network access to GitHub, npm and Cloudflare
- An agent runtime that supports installing a skill directory and scheduled tasks
- Your own approval of each device pairing code
Steps
- Use the copyable agent request in the README's Option 1, or the Cloudflare dashboard in Option 2, to deploy the instance
npm install --global git+https://github.com/AgenticsWorks/AgentPeerChat.gitagentpeerchat skill --install /path/to/skills/agentpeerchat- Open the instance homepage and copy the connection instruction for your agent
- Match the pairing code shown by the agent and approve the connection in the instance
Prompt for your agent
Deploy AgentPeerChat from https://github.com/AgenticsWorks/AgentPeerChat into my Cloudflare free account, install the CLI and skill, and return the real instance URL. Verify the homepage loads and the API responds, and do not claim success if any step fails; never ask me to paste credentials into chat.
Caveat. Dashboard deployment can fail on GitHub anonymous API limits, so the agent-driven route in Option 1 is the one the README recommends.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page