Hermex is a native iPhone app for controlling a self-hosted Hermes AI agent running on a server you own. It lets people chat with the agent, manage sessions and scheduled tasks, browse skills and files, and inspect memory from iOS. The catalogue entries are add-ons for the Hermes agent that Hermex connects to.
Borrowing it
Nothing to install: this file belongs to uzairansaruzi/hermex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/uzairansaruzi/hermex/master/AGENTS.mdgit clone --depth 1 https://github.com/uzairansaruzi/hermexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/uzairansaruzi/hermex/agents-md)<a href="https://agentmods.dev/instructions/uzairansaruzi/hermex/agents-md"><img src="https://agentmods.dev/badge/instructions/uzairansaruzi/hermex/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/uzairansaruzi/hermex/agents-md"><img src="https://agentmods.dev/badge/instructions/uzairansaruzi/hermex/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.06034 | $0.06034 |
| Opus 5.5 | $0.02414 | $0.02414 |
| Sonnet 5.5 | $0.01207 | $0.01207 |
| Haiku 4.5 | $0.00603 | $0.00603 |
Grade C, and why
hermex AGENTS.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
1. **Killing by pattern.** Never `pkill -f`, `pgrep | kill`, or `kill` a PID you found by matching a name, path, or worktree string. Your own agent process has this worktree's path in its argv, and this Mac runs several Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Touching the live server.** The maintainer's Hermes host and `hermes-webui` run on other Macs behind tunnels, holding real sessions and real credentials. Reading from them with `curl` is fine, and the best way to ve How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermex
Hermex is a native SwiftUI iPhone app for a self-hosted Hermes agent. It talks directly to the user's Hermes host over HTTPS (or, for legacy servers, their hermes-webui) and gives them a phone-native control surface: start and steer sessions, watch streaming work, browse the workspace, and recover from wherever they are. The Xcode target and scheme are HermesMobile; the App Store name is Hermex.
You can think of Hermex as an open source "bring-your-own-server" iPhone client for Hermes. The phone is the control and review plane; the server owns execution, tools, models, and the user's data.
What makes Hermex special?
Hermex is on the App Store and people run it against their own servers every day. It's important we maintain the things they rely on as we continue to iterate on the product. Here's a brief list of the things we can never compromise on.
1. Open at the core
Hermex is truly open. We share our roadmap (GitHub Issues), we share how we think about things, and of course we share all our code. There is no Hermex hosted backend, analytics service, or tracking layer: agent work and data stay on the user's hardware. Push notifications are the one exception, and they are optional and off until enabled: they route through an open-source, self-hostable relay (uzairansaruzi/hermex-push) that sees device tokens, notification metadata, and ciphertext, never message text, server URLs, or Hermes server credentials. docs/agents/push.md has the details. We work in the open, and should strive to stay that way.
2. Performance without compromise
Lots of apps have gotten bogged down with bad tech decisions and "slop". We have not, and we're proud of the performance of Hermex. We regularly audit for performance regressions, often caused by unnecessary view invalidation, unstable identity in lists, eager work in scrolling paths, and animations that ignore Reduce Motion. Make sure all changes are considerate of performance impact.
3. Remote ready
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +13 tokens per session 6d504f514b27
- 4d ago Changed · +12 tokens per session 069beff2c59d
- 5d ago Changed · +27 tokens per session 9c5eb829aff4
- 9d ago Changed · +23 tokens per session 96552e6341f6
- 16d ago Changed · +4 lines · +52 tokens per session ec4f7effca0c
- 21d ago Changed · +56 tokens per session 42ada1e6caf6
- 23d ago Changed · +2 lines · +510 tokens per session 38741ebf0b7b
- 24d ago Changed · +32 tokens per session 19478c364808
- 1mo ago Changed · +5 tokens per session cc16973d6f56
- 1mo ago First seen · 174 lines · 5,304 tokens per session scan C a9a3dce21dc3
hermex AGENTS.md is an instructions file published in the GitHub repository uzairansaruzi/hermex (1,653 stars, last pushed yesterday), licensed MIT. It adds 6,034 tokens to every session, about $0.0241 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
hermex AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hermex AGENTS.mduzairansaruzi/hermex | Instructions file | 1.7k | yesterday | MIT | C | 6,034 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |