
Agents don't care about vendors - they want the best API for the task. treg gives your agent 2,600+ tools (SEO, social, leads, ads, scraping) behind one URL and one token. Search by task, see price/request/response, pay per call at 0% markup. Open source.
Loading comments…
Project Info
Product Keywords
Treg is an open-source API gateway that gives AI agents access to 2,630+ tools from 47 different providers behind a single URL and one token. Think of it as OpenRouter for agent tools—instead of signing up for Semrush, Moz, Hunter, and a dozen other services separately, your agent gets one credential that unlocks the entire catalog. Each tool is priced per call, with the cost shown upfront, and Treg adds no markup on top of what providers charge.
Forty-seven providers, one credential. Your agent holds a single Treg token, and every tool in the catalog answers to it. No per-provider signups, no key files scattered across machines, and you can revoke everything in one place.
Your agent asks for the task, not the tool. Nineteen providers sell backlinks, nine sell email lookup—Treg shows what each one charges and measured performance data like success rate and speed. Your agent picks based on evidence, not guesses.
No subscriptions. Treg carries the provider subscriptions and bills you fractions of a cent per call, with the price shown before each request. You get $1.00 free to start, and if you already pay for a provider, you can bring your own key and route those calls through it unmetered.
The entire platform is open source, so you can inspect how it works, self-host if you prefer, or contribute to the catalog. The provider list and pricing are transparent—nothing hidden behind enterprise sales calls.
Treg turns 47 vendor subscriptions into one token—your agent picks the best tool for the job, not the best sales pitch.
The comparison layer is the real differentiator. Most API aggregators just proxy requests; Treg actively measures each provider's success rate, speed, and reliability, then presents that data to your agent at decision time. That means your agent can switch from a slow or failing provider to a better one automatically, based on live evidence rather than vendor marketing.
You're building agents that need real-world data—SEO rankings, backlinks, social trends, lead enrichment, or ad management—and you're tired of stitching together five different API SDKs. If you've ever abandoned a tool idea because the provider required an enterprise sales call or a $200/month minimum, Treg removes that barrier entirely. It's also worth a look if you want to compare providers on actual performance data before committing your agent's workflow to one vendor.
Other tools you might consider
Ditch your scraper. One API gives your code everything it needs from the web: structured JSON, clean markdown, cited research, and browser automation. No browser, LLM, or pipeline for you to run. Use it from the tools you already work in: an MCP server, CLI, Raycast extension, or as an Agent Skill. Grab a key and make your first call in less than three minutes. Mozilla-backed. Your data is never sold, never trained on.
The moment an agent needs to deploy something, it slams face-first into a wall built for humans. Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds.
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
Navegación basada en árboles, refactorización semántica, análisis de código base y herramientas de portabilidad de lenguajes para agentes de codificación que admiten 163 gramáticas.
Maker
sandbyte
Loading comments…