#2121st of 48 in Gateways and observability
treg
Tool registry proxy giving agents one token for a priced API catalog
- Stars
- 7.8k
- License
- custom license
- Last commit
- Nov 2026
- Language
- Python
51 on 14 Jul 20267,829 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
treg is a proxy and CLI that lets an agent call a catalog of third-party endpoints (SEO, enrichment, scraping, ads, media generation) with one token, billed per call from a prepaid balance. Teams can also register their own API keys, vendor CLIs and SKILL.md bundles, with credentials injected server-side so callers never hold them. It can be self-hosted as a Python server with SQLite, or used via the hosted treg.to.
Who it is for: Teams giving agents shared, metered access to third-party APIs and CLIs
Strengths
- Credentials are injected server-side; callers and agents never see provider keys
- Own key takes precedence over treg's and is never metered
- Per-call pricing shown in catalog; 402 response carries balance and top-up URL
- Ships CLI, Claude Code plugin, MCP endpoint and ready-made workflow skills
Weaknesses
- Catalog access relies on treg's provider accounts via hosted treg.to, not self-hosting alone
- License is NOASSERTION, so reuse terms are unclear
- Server-side CLI execution is disabled globally; CLIs run locally only
- Sends anonymous usage to PostHog by default when using treg.to
What it needs
- no GPU
- Needs uv, tmux, Node 22.12+ (dashboard build), SQLite, PostHog (CLI telemetry, optional)
- port 18790
Quick answers
Is treg open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Does treg need a GPU?
No, it runs without one.
Also in Gateways and observability
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | OmniRouteLLM gateway routing one OpenAI-compatible endpoint across 372 providers | 96 out of 100 |
| 2 | headroomCompresses tool outputs, logs and history before they reach the LLM | 92 out of 100 |
| 3 | new-apiGateway that unifies LLM providers behind OpenAI, Anthropic and Gemini APIs | 91 out of 100 |
| #4 | MLflowTracing, evaluation and prompt registry for LLM apps, plus ML tracking | 90 out of 100 |
| #5 | LiteLLMOpenAI-format gateway and Python SDK for calling 100+ LLM providers | 87 out of 100 |