treg is a unified, pay-per-call tool catalog that lets AI agents access 4,000+ endpoints from 113 providers for SEO, social, enrichment and ads data with one key.
About
treg is an open-source tool catalog and unified API gateway designed for AI agents. It solves a common problem in agent-based workflows: many useful data sources — keyword research, backlink data, social trends, email verification, ad campaign management — sit behind per-provider subscriptions, signup walls, or APIs with no public access at all. Instead of buying individual seats at services like Semrush, Moz, or Hunter for a single automated task, an agent calls treg with one token and pays a fraction of a cent per call.
The service describes itself as "OpenRouter for agent tools," referencing the model-router platform but applied to data and tool endpoints instead of language models. treg lists more than 4,000 endpoints across 113 providers covering SEO and SERP data, backlinks, AI search visibility, social media, people and company enrichment, advertising, and scraping. Credentials are injected server-side, so no provider key is stored on the agent's machine, and the platform adds a 0% markup on provider rates. The project is licensed under AGPL and is developed in the open on GitHub.
Key Features
Pricing & Fees
- Pricing: Usage-based. Most lookups cost fractions of a cent (examples listed: keyword volume at $0.006/call, backlinks at $0.012/call, email verification at $0.004/call), with a 0% markup over provider rates.
- Free start: $1.00 of free credit is offered once per new verified account.
- Open source: The project is 100% open source under the AGPL license.
- Sign-in options: GitHub, Google, or an emailed one-time code.
Who It's For
treg is built for developers and teams running AI agents that need live external data — local coding agents such as Claude Code or Cursor, and hosted assistants that support custom MCP connectors. Typical users include SEO specialists automating keyword and rank research, growth marketers pulling social trends and ad data, and sales teams automating lead enrichment and email verification. It also suits teams that want to share internal APIs and skills without distributing credentials, since registered tools stay callable while keys remain on the server.
FAQ
What is treg?treg is an open-source catalog and unified gateway that lets AI agents call 4,000+ endpoints from 113 data providers — covering SEO, backlinks, social media, enrichment, and ads — using a single token and pay-per-call pricing.
How much does treg cost?Billing is usage-based with no subscription: prices are quoted before each call, most lookups cost fractions of a cent, and treg adds a 0% markup over provider rates. New verified accounts receive $1.00 of free credit.
Which platforms and agents does treg support?It works with hosted assistants via its MCP endpoint (`https://treg.to/mcp/`), and with local coding agents such as Claude Code, Cursor, and Codex through a CLI installer and skills.
Can I use my own provider keys?Yes — if a team already holds a key for a provider, those calls route through it, are unmetered, and take precedence over treg's own account (with one stated exception: X connections through treg's app are billed per call).
How does treg handle credentials and security?Credentials are injected server-side and never stored on the agent's machine, every call is audited, and the whole platform is open source under AGPL for inspection.
Related Tutorials
View all →
Related Tools
View all →
OmniRoute - Free AI Gateway for Multi-Provider LLMs Free, open-source AI router with auto-fallback. 236 providers, one endpoint, 95 MCP tools, 17 routing strategies, A2A protocol, auto-combo engine, semantic cache, memory & skills. Deploy anywhere. 
OpenHands Open-source, model-agnostic platform for building and deploying cloud coding agents. Automate real engineering work securely with full transparency and control. 
Agent-Native Apps Framework Build agentic apps where AI agents and UI share the same database and state. Open source framework with ready-to-fork templates. 
DeerFlow - Agent Framework A LangChain-based framework for building super agents. Streamlines the development of advanced AI agents with ease. 
FunASR - End-to-End Speech Recognition Toolkit Industrial-grade speech recognition toolkit. 170x realtime on GPU, 50+ languages, speaker diarization, emotion detection, OpenAI-compatible API, vLLM acceleration, and agent integration.