Status
Is Mel working right now?
This page asks Mel's hosted AI service one question and prints the answer with the time it was asked. That is a reading taken at a moment, not an uptime report — we keep no availability history, so we publish none.
The Mel relay is the hosted service the Mel agent sends model calls through. It answered our check in 791 ms at Sep 8, 2026, 18:45 UTC.
One check, at most once a minute, and only while someone is reading this page. Nothing here is watching between your visits.
What the download service is publishing right now. Download or read what changed.
Our changelog's newest entry is v0.1.36. When these two differ, the download service is the one that decides what you get.
That is the only claim this page can honestly make about itself. It is served by the same host as the rest of openmel.dev, so if that host has an outage this page goes down with it and cannot report it.
Latest changes
- Connectors. Settings ▸ Connectors lists the partner tools Mel Connect offers — ElevenLabs first. Press Connect, sign in with your own account in your browser, and its tools appear to Mel behind the same permission cards as everything else. Your sign-in stays on this computer; disconnect any time.
- A connector is asked about every time it is used. The card names the company and the exact tool — “ElevenLabs wants to: text_to_speech” — and says plainly that this sends your request to another company. There is no “always allow” for a connector, and a tick you gave a shell command earlier does not cover one.
- Run your own tool server. Custom server… at the bottom of the Connectors page points Mel at a program on your own machine. Values you enter that look like keys go to your keychain, not into a settings file.
- The model picker now lists every chat model the ten providers serve (143 ids, up from 61) with the providers’ true context windows — nine were too small (DeepSeek V4 is 1M, not 128k) — and the three ids no provider serves any more (Groq’s two Llama ids, Kimi K2.5) are gone. Picking a legacy id still works; auto only ever picks a model with a verified price and window.
- The picker also lists NVIDIA’s NIM catalog (55 models: Nemotron 3.5 Lightning, Nemotron 3 Super / Ultra / Nano Omni and every other chat model the endpoint serves — Kimi K3, DeepSeek V4, MiniMax M3, Gemma, Llama, Mistral, Phi, Granite and more, marked (nvidia)). They can be pinned; auto never picks them yet — until Mel’s NVIDIA key and terms are in place a pinned NVIDIA model falls over to the usual chain with a visible “why this model” note.
- auto reads the task instead of making one fused guess — what kind of work it is, how hard, how many tool rounds it will take, how big it is. A long conversation no longer makes a short question expensive: that one mistake was 75 of the 164 misroutes we measured. Mel’s own “keep going” continues on the previous turn’s terms, and a turn with an image in it is routed once, onto a model that can see it.
- auto now tells every provider whether to think. A quick question or a small edit gets a no-thinking answer on every model that can be told to stop — DeepSeek, GLM, Kimi K2.6, MiniMax M3, Qwen, Gemini 2.5, the GPT-5.x line, Claude — while a build or a hard problem gets a small or medium thinking budget. Your own reasoning-level pick always wins. MiniMax models no longer show their reasoning inside the answer.
- Bring-your-own-key users can now set an NVIDIA key.
Before that: v0.1.35, v0.1.34. Every release.
What this page does not tell you
- No uptime percentage, and no history. We don't collect a public availability series, so there is no honest number to put here. A figure with decimals that nothing measured is worse than silence.
- No incident log. When something goes wrong we write it up in the changelog of the release that fixes it, in plain words, including the releases that did harm.
- Nothing about Mel on your machine. The terminal, your command blocks, and any CLI coding agent you run inside Mel execute locally and never touch the service checked above. A bad reading here does not stop them; only the Mel agent's hosted models depend on it.
- Nothing you should read as an alert. This is a page you visit, not a monitor that watches for you. If Mel is failing for you, tell us — that still reaches a person faster than this page will.