treg
by superdesigndev
Treg is a proxy and registry that gives AI agents one web address and one token to call thousands of paid tools, such as SEO data, company enrichment, scraping and image generation. It charges a small fee per call, so you don't need separate accounts with each provider, and it can also hold your team's own keys and command-line tools on the server.
- Stars
- 6.3k
- Licence
- Apache-2.0
- Runs on
- A cloud service
- Setup
- Moderate
- Language
- Python
- Age
- 103 days
What you can do with it
- Search a catalogue of tools by task, such as backlinks for a domain, and call them with one token
- Store your team's API keys and command-line tools on the server so agents can use them without seeing the keys
- Run ready-made agent skills for lead finding, recruiting shortlists, web research and AI video ads
Could replace
- Semrush
- Moz
- Crunchbase
Our suggestion based on what it does, not a feature-by-feature comparison.
Make money with it
A freelancer could offer lead research, SEO audits or short AI-made video ads to clients, using treg for the data and generation at a few cents per call.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Pull SEO, backlink and company data per call instead of paying monthly subscriptions to several data vendors
- Let staff agents share one set of company credentials safely, without handing keys to each person
Can you use it commercially?
Free to use, change and sell (Apache 2.0 in the licence file). Some folders may carry other terms.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install the command-line tool with a curl script from treg.to and sign in, or add it as a Claude Code plugin; you can also self-host the server.
Follow the official instructions in the project README.
Things to check
- Licence is not clearly stated
- The catalogue is paid per call, with only $1 free credit for new teams
- Relies on the hosted service at treg.to unless you self-host
- Some catalogue tools involve scraping social platforms, which may break those platforms' terms
- Credentials are held server-side, so you must trust whoever runs the server
Who's talking about it
Checked 27 Oct 2026. Summary drafted by AI from the project's README.
