Newborn Newborn TypeScript TS
↑ 31
hermes-mobile-app omarqaterge/hermes-mobile-app

Your agent, on your phone. A native Android app for Hermes Agent, running entirely on-device (Termux).

HEALTH 80 / Healthy
// solo builder// hidden gem// release machine ai-agentandroidhermes-agentllmtermux
10-2026 · today · omarqaterge
★52 Share View on GitHub ↗

// readme

No laptop. No server.

Unofficial community project. Not affiliated with or endorsed by Nous Research. Hermes itself is never patched.

Why

Hermes Agent is a powerful agent, but it lives in a terminal. Hermes Mobile gives it a proper phone interface: streaming chat, live tool cards, approvals you can answer from the status bar, a canvas for building things together, and notifications that work while the app is closed. Hermes runs in Termux on the same phone, so the whole thing is self-contained.

Highlights

Answer from the island

Approvals and questions show up on the status chip (an Android 16 Live Update; older versions get a normal notification). One tap on the chip, pick an answer, done. The app does not need to be open.

Renders everything, natively

KaTeX equations, sortable tables with “Copy table”, tick-able task lists, Obsidian-style callouts, Mermaid diagrams (full screen, pinch to zoom), coloured diffs, long code that collapses, inline SVG and HTML cards.

A canvas you and Hermes share

Ask for an interactive page or a 3D scene and Hermes builds it live in a document beside the chat. HTML runs in a sandbox that is offline unless you allow it.…

↑ The Undervalued Score +

How much a project earns versus how much attention it actually gets. Above 50 means the work is outrunning its audience. Recomputed nightly from commit velocity, contributor effort, issue resolution, fork utility, release cadence, and project maturity — divided by a logarithmic reach factor.

score  = signal / reach

signal = 0.25·commit_velocity   // commits in last 90 days (cap 30)
       + 0.20·contributor_work  // unique authors × velocity (cap 100)
       + 0.20·issue_resolution  // closed ÷ total issues
       + 0.20·fork_ratio        // forks ÷ stars (proxy for real usage)
       + 0.10·release_cadence   // releases in 90 days (cap 3)
       + age_bonus              // +0 to +0.30 after 6 months
       + homepage_bonus         // +0.05 if homepage is set

reach  = log₁₀(stars + watchers + 10)█
♥ The Health Score +

Is the project alive and maintained right now? A 0–100 pulse recomputed nightly from commit recency, rhythm, how fast issues close, and how quickly PRs get merged.

health = 0.35·recency       // days since last commit (90d decay)
       + 0.25·cadence       // commit rhythm consistency
       + 0.20·issue_health  // closed ÷ total issues
       + 0.20·pr_health     // merged ÷ total PRs█
◷ Health bands +

The colour and label on every card come straight from the health score.

Healthy   80 – 100   active, responsive, regular releases
Stable    60 – 79    maintained, steady, no alarms
Quiet     40 – 59    slowing down — watch this one
At Risk    0 – 39    going dark · candidate for rescue█
// Tags — what each label means +

Tags are independent behavioral signals computed nightly. A project can hold multiple at once. They drive the home page sections.

solo_builder      one person holds > 80% of commits (last 180d)
needs_contributors has open "help wanted" or "good first issue" labels
hidden_gem        < 100 stars · active in last 3 months · documented
legacy_hero       repo > 5 years old · committed this year
fork_magnet       forks/stars > 0.5 · used as template or dependency
release_machine   5+ releases in the last 90 days
under_pressure    > 10 open issues · ≤ 2 contributors · health ≥ 60
community_watch   watchers > stars · devs tracking before the public
community_hub     GitHub Discussions enabled · > 20 discussions
funded            maintainer has active funding channel█
★ Why rank against stars at all? +

Stars are an outcome, not effort. A project with 8 stars and daily commits is doing more interesting work than one coasting on 8k. We measure the building, then divide by the attention already received — so the genuinely undervalued rise to the top.

// stars   = lagging indicator
// commits = leading indicator
// we rank by the leading one█