What is hermes-custom-providers?

A setup guide for connecting Hermes Agent to an OpenAI-compatible API provider that is not already built in. An API is a way for one program to request services from another program.

Use it to add a custom provider, set its API endpoint and key, and select one of its models in Hermes.

It lets Hermes use providers outside its standard list while keeping their address, model, and access key configured separately. It also explains where the protected configuration files belong.

hermes-custom-providers — Skill for Claude Code and Codex by S3YED

Install

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.

Any agent

npx skills add S3YED/appie-kit --skill hermes-custom-providers

Clone the repo

git clone --depth 1 https://github.com/S3YED/appie-kit

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/s3yed/appie-kit/hermes-custom-providers/github.svg)](https://agentmods.dev/skills/s3yed/appie-kit/hermes-custom-providers)

Your own site

<a href="https://agentmods.dev/skills/s3yed/appie-kit/hermes-custom-providers"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/hermes-custom-providers/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/s3yed/appie-kit/hermes-custom-providers"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/hermes-custom-providers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,297 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00029	$0.01297
Opus 5	$0.00015	$0.00648
Sonnet 5	$0.00006	$0.00259
Haiku 4.5	$0.00003	$0.00130

Measured 7d ago against content hash cee6c4f9100f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

hermes-custom-providers scanned grade B 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 /root/.hermes/.env

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -w "\nHTTP:%{http_code}" https://api.example.com/v1/chat/completions \

skills/autonomous-ai-agents/hermes-custom-providers/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Custom Providers

Configure any OpenAI-compatible API as a first-class Hermes provider. Use when the provider you need (Sakana, Together, Fireworks, Groq, Perplexity, etc.) isn't one of the built-in 20+ providers.

Quick Reference

hermes config set custom_providers.<name>.type "openai"
hermes config set custom_providers.<name>.base_url "<url>"
hermes config set custom_providers.<name>.api_key '${ENV_VAR}'
hermes config set model "custom:<name>/<model_name>"

Step-by-Step

1. Set the API key in `.env`

The .env file lives at /root/.hermes/.env (not /root/.env).

printf 'MY_API_KEY=sk-...\n' >> /root/.hermes/.env
chmod 600 /root/.hermes/.env

IMPORTANT: Do NOT use the write_file tool or patch tool to write to .env — both are blocked for security (it's a protected credential file). Use printf or cat via the terminal tool.

2. Configure the provider

Use hermes config set — the patch tool and write_file tool are BOTH blocked from editing /root/.hermes/config.yaml:

hermes config set custom_providers.<name>.type "openai"
hermes config set custom_providers.<name>.base_url "https://api.example.com/v1"
hermes config set custom_providers.<name>.api_key '${MY_API_KEY}'

Required fields:

Field	Value	Notes
`type`	`openai`	Must be `"openai"` for OpenAI-compatible APIs
`base_url`	`https://.../v1`	The full API base URL, NOT just the host
`api_key`	`'${ENV_VAR}'`	Reference to env var — use single quotes in `hermes config set` to prevent shell expansion

Optional fields:

Field	Notes
`models`	List of model names: `- fugu` `- fugu-ultra`
`reasoning_effort`	Some providers support `high`/`xhigh`

3. Set the model reference

hermes config set model "custom:<name>/<model_name>"

The format is always: custom:<provider_name>/<model_name_string_sent_to_api>

Example for Sakana Fugu:

hermes config set model "custom:sakana/fugu"

Read the full file on GitHub · 127 lines

Changes

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.

7d ago First seen · 127 lines · 29 tokens per session scan B cee6c4f9100f

Subscribe to this mod's changes

hermes-custom-providers is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 1,297 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Data and AI agent-skills ai-agent ai-employee ai-employee-kit anthropic api config custom hermes openai-compatible providers sakana

claude-api-cost-optimization

Save 50-90% on Claude API costs with Batch API, Prompt Caching & Extended Thinking. Official techniques, verified.

Louishin/claude-api-cost-optimization · 33 tokens

openrouter

OpenRouter unified AI API - Access 200+ LLMs through single interface with intelligent routing, streaming, cost optimization, and model fallbacks.

bobmatnyc/claude-mpm-skills · 32 tokens

openai-patterns

Production OpenAI API patterns — model selection, prompt engineering, function calling, streaming, error handling, cost control, and structured outputs.

chandrudp29/skillhub · 31 tokens

kimi-code-api

Integration guidance for Kimi Code, a coding model service, using its login flow, tokens, chat requests, and model-list requests.

LSTM-Kirigaya/jinhui-skills · 80 tokens

claude-api

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.

zebbern/termstack · 84 tokens

llava

Vision-language chat: VQA, captioning, image dialogue.

NousResearch/hermes-agent · 16 tokens

hermes-custom-providers