My take
For self-hosting TURN, I'd run coturn and not think twice. It's what everyone runs, it does everything, and the whole ecosystem assumes it. STUNner is worth your time - it has the best docs and a genuinely modern, Kubernetes-native design, and not one AI model has heard of it.
Not sure which way to go?
This page tells you what AI sees. I can help you fit it to your call volume, your budget, and your team.
| Tool ▲ | AI Visibility iHow often AI recommends this tool - the average of three model scores from 0 to 10: Claude Sonnet 4.6, Gemini 2.5 Flash and GPT-4o. One tool dominates and most score near zero, which is the point.▲ | Quality iA measured score from 0 to 100, blending documentation depth (docs) and feature coverage (feat).▲ | Agent-ready iWhether the project ships something that lets an AI agent build with or operate it: an agent skill or MCP server (full), or just an llms.txt docs file (adjacent). Almost nobody here does.▲ | Popularity iRaw project reach, measured June 2026: GitHub stars and forks. None of these tools ship an npm package, so there is no download signal. Not composited into a score.▲ | Liveliness iHow active the repo is right now, measured June 2026: time since the last commit and the number of commits in the last 4 weeks.▲ | Tsahi's note ▲ |
|---|---|---|---|---|---|---|
coturn | 8.3avg | 81 63%89% | None | The Default | ||
Pion TURN | 1.0avg | 63 54%67% | None | No call here - measured, not judged | ||
restund | 1.0avg | 53 50%54% | None | Past Tense | ||
eturnal | 0.7avg | 71 67%72% | None | No call here - measured, not judged | ||
STUNner | 0.0avg | 81 88%78% | None | A Hidden Gem |
Documentation depth
Feature coverage
Claude Sonnet 4.6
Gemini 2.5 Flash
GPT-4o
MEASURED
- Project health (stars, forks, commits) was pulled from GitHub in June 2026. These figures move daily
- AI Visibility and Quality come from my evaluation runs in the same window
None of that is a score. It's a recommendation. The grades on this page measure the machines, not my opinion of the vendors.
