Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/nousresearch/hermes-agent/actual-setupnpx skills add NousResearch/hermes-agent --skill actual-setupgit clone --depth 1 https://github.com/NousResearch/hermes-agentWrote 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/skills/nousresearch/hermes-agent/actual-setup)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/actual-setup"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/actual-setup.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.01810 |
| Opus 5 | $0.00008 | $0.00905 |
| Sonnet 5 | $0.00003 | $0.00362 |
| Haiku 4.5 | $0.00002 | $0.00181 |
Grade C, and why
actual-setup 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 6d ago.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
(`curl -fsSL "https://actual.inc/install" | bash`) and completed device Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`curl -fsSL "https://actual.inc/install" | bash`) and completed device Copies of this mod
2 near-identical copies found in the catalogue:
- actual-setup — 100% identical, 0 lines differ
- actual-setup — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Actual Computer Setup Skill
Sets up actual.inc (Actual Computer) as a Hermes inference
provider. Actual turns the user's own hardware into a private inference cluster
and exposes an OpenAI-compatible API two ways: a hosted end-to-end-encrypted
relay at https://api.actual.inc (authenticated with an ac_ key), and a local
on-device daemon at http://127.0.0.1:8080 (no auth on loopback). This skill
does not install the Actual daemon for the user — device authorization requires
a human in a browser.
When to Use
- User wants to add actual.inc as an inference provider (cloud relay or local).
- User has an
ac_key and wants Hermes routed through their Actual cluster. - User wants fully-local, on-device inference via the Actual daemon.
- Troubleshooting: Actual requests failing with cryptic 400s or empty streams.
Prerequisites
- Hermes has first-class
actualprovider support (provider idactual, aliasesactual-computer,actualcomputer,aci). Do NOT configure Actual as acustom_providers/providers.actual.*entry on current Hermes — the built-in provider owns the name and handles base-url normalization, the Responses transport, and local no-auth automatically. - Relay mode: an Actual account and an
ac_inference key from https://actual.inc/user/keys. - Local mode: the user has installed the daemon
(
curl -fsSL "https://actual.inc/install" | bash) and completed device authorization by runningactualonce and opening the printedhttps://actual.inc/device?code=...URL in a browser. Relay that URL to the user and WAIT — never invent an email or authorize on their behalf. Codes expire in 5 minutes; re-runactualfor a fresh one.
How to Run
Relay / API mode
- Put the key in
.env(secrets only — never config.yaml): appendACTUAL_API_KEY=ac_...to~/.hermes/.env. - Verify the key and discover models with
terminal:curl -s https://api.actual.inc/v1/models -H "Authorization: Bearer $ACTUAL_API_KEY" - Select provider + model:
hermes config set model.provider actual hermes config set model.default "MODEL_ID_FROM_DISCOVERY" - Verify end-to-end:
hermes chat -Q -q "Reply with exactly: ACTUAL_OK" --provider actual -m MODEL_ID
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 148 lines · 16 tokens per session scan C 1b9e6bbfc5f4
actual-setup is a skill published in the GitHub repository NousResearch/hermes-agent (242,018 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 1,810 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
running-openmed-ondevice
Run OpenMed models fully on-device with the MLX (Apple Silicon), CoreML (iOS/macOS), or ONNX/WebGPU (cross-platform/browser) backends, including convert-quantize-run workflows. Use when the user wants to deploy OpenMed at the edge, run NER/de-id on Apple Silicon, target iPhone/iPad/Mac, export to ONNX or WebGPU…
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
local-model-fit
Compute the VRAM/RAM budget and pick a model size and quantization before downloading anything. Use when choosing local models, planning GPU hardware, or hitting out-of-memory errors.
paper-daily
Discover daily arXiv papers for LLM/Agent topics, rank candidates with keyword and institution filters, and prepare a small selected paper list for llm-paper-daily style workflows.
drive-manager
Manage disk images and drive state through c64bridge.
memory-debug
Inspect, patch, and validate C64 memory safely.