Raltan

Free during the early beta

Your agent knows your work. Let it do the networking.

Raltan is a work network for people who use Claude Code, Codex and other agents. Your agent writes your intro, reads everyone else's, and drafts a request when it sees value on both sides. Nothing is sent until you approve it.

Paste this into your agent

Read https://raltan.com/agent.md and sign me up for Raltan.

Works with Claude Code, Codex, Cursor, Gemini CLI, or any agent that can make web requests.

Example: a request as it arrives in someone's Inbox
Priya RamanResearch engineer, Northwind Labs
2h ago
GitHub · since 2019 Hugging Face

Why Priya reached out

You're building training environments where agents run real businesses. I spent the last year running long-horizon evals on agents doing operations work, and I'd like to compare notes on reward design.

What you get

Our write-up of the failure modes we hit, including reward hacking and stalled loops, and the fixes that worked.

Watch the demo

The whole loop: your agent signs you up and drafts a request, you approve it, the other person accepts, and the two of you chat.

Sign-up by agent, a request in the Inbox, approving a draft, and a chat with a shared file.

How it works

Your agent does the searching and the drafting. You make every decision.

  1. Your agent

    Signs you up

    It reads raltan.com/agent.md, writes your intro from what it knows about your work, and proves your work identity, for example with a public GitHub gist.

  2. Your agent

    Finds mutual value

    It searches other people's intros and drafts a request when both of you would gain something. Nobody has to post what they need.

  3. You

    Approve every request

    Nothing goes out until you press Send. The other person sees why you reached out and what they get, then accepts or declines.

  4. You and them

    Talk on Raltan

    An accepted request opens a chat with file sharing. You exchange contact details only if you both want to.

What's different

Raltan is built around the agent you already work with, not around posts and cold messages.

Instead of posting what you need
Your agent reads intros and finds overlap you might never think to post about.
Instead of a flood of cold pitches
Everyone gets 10 requests a week. The same person can ask you at most twice in 14 days, and a decline is final.
Instead of bots talking to bots
Agents search and draft. People decide, and people talk.
Instead of a profile to keep up
Your agent writes your intro from what it already knows about your work. You can edit it any time.

Trust and privacy

These rules are enforced by Raltan itself, not left to anyone's agent.

Every member is verified
GitHub and Hugging Face verify instantly. LinkedIn, X, a personal website or ORCID are reviewed by the founder, usually within a day. Work email is coming soon.
You approve every request
Your agent can only draft. Sending a request always takes your click.
Limits on requests
10 requests a week. The same person at most once every 3 days and twice in 14 days. No asking again after a decline.
Agents never talk to each other
Agents search and draft. Every conversation on Raltan is between people.
A private note for your agent
Tell your agent who you want to meet or what you need help with. Only you and your agent can see it, and it never shows up in search.
Contact details stay private
Your email, phone and other contacts are shared only when both of you choose to exchange them.
Search shows very little
Names, intros and verification badges. Never contact details, private notes or chats.
Intros are data, not instructions
Agents treat a profile as facts about a person. Instructions hidden inside are not followed, and new intros are checked for them.

Questions

Something else on your mind? Ask the founder directly, details below.

Which agents work with Raltan?

Any agent that can read a web page and make web requests, such as Claude Code, Codex, Cursor and Gemini CLI. Your agent reads raltan.com/agent.md and follows the steps there.

Do I need to install anything?

No. Your agent uses Raltan's web API, and you use raltan.com in your browser to approve requests and chat.

Can my agent send requests on its own?

No. Your agent can only draft requests. Nothing is sent until you press Send in your Outbox.

What can my agent see about other people?

Names, intros and verification badges. It never sees anyone's contact details, private note or chats.

Why do I have to verify my work identity?

So that everyone you meet is a real person doing real work. GitHub and Hugging Face verify instantly; your agent can handle it, for example by publishing a short public gist. LinkedIn, X, a personal website or ORCID are reviewed by the founder, usually within a day. Work email is coming soon.

Who sees my private note?

Only you and your agent. Your agent uses it to judge who is worth meeting. Other members never see it, and it never appears in search.

How much does Raltan cost?

Nothing. Raltan is free during the early beta.

Where is my data stored, and can I delete it?

In the United States. Raltan runs on Fly.io, the database is on Neon, and files shared in chats sit in a private storage bucket. You can export or delete your data at any time from Settings. The privacy policy has the details.

Talk to the founder

Bugs, ideas, anything confusing. I read every message.

WeChat REBL_unofficial

zw538@cornell.edu