by ZoniBoy00
Abacus AI image generation plugin for Hermes Agent - FLUX, DALL-E, MidJourney and 20+ models
# Add to your Claude Code skills
git clone https://github.com/ZoniBoy00/hermes-agent-abacus-aiGuides for using ai agents skills like hermes-agent-abacus-ai.
hermes-agent-abacus-ai is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ZoniBoy00. Abacus AI image generation plugin for Hermes Agent - FLUX, DALL-E, MidJourney and 20+ models. It has 0 GitHub stars.
hermes-agent-abacus-ai's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/ZoniBoy00/hermes-agent-abacus-ai" and add it to your Claude Code skills directory (see the Installation section above).
hermes-agent-abacus-ai is primarily written in Python. It is open-source under ZoniBoy00 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh hermes-agent-abacus-ai against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Generate high-quality images directly in Hermes Agent using Abacus AI's RouteLLM API. Supports FLUX 2 Pro, DALL-E, MidJourney, and 20+ other image generation models through a single OpenAI-compatible endpoint.
image_gen providerCopy and paste this prompt to your Hermes Agent (Telegram, Discord, or CLI). It will clone the repo, copy the files, configure everything, and restart the gateway automatically:
Install the Abacus AI image generation plugin from the public GitHub repo https://github.com/ZoniBoy00/hermes-agent-abacus-ai. Clone the repo to /tmp, copy the abacus_ai/ directory to ~/.hermes/plugins/image_gen/abacus_ai/, enable image_gen/abacus_ai in plugins.enabled in config.yaml, set image_gen.provider to abacus_ai, configure custom_providers with name abacus-ai using my API key, then restart the gateway.
Make sure you have your Abacus AI RouteLLM API key ready — Hermes will ask for it during installation.
git clone https://github.com/ZoniBoy00/hermes-agent-abacus-ai.git /tmp/hermes-agent-abacus-ai
abacus_ai/ directory to your Hermes image_gen plugins folder:cp -r /tmp/hermes-agent-abacus-ai/abacus_ai ~/.hermes/plugins/image_gen/abacus_ai/
~/.hermes/config.yaml:plugins:
enabled:
- image_gen/abacus_ai
hermes config set image_gen.provider abacus_ai
custom_providers:
- name: abacus-ai
api_key: "your-api-key-here"
base_url: "https://routellm.abacus.ai/v1"
systemctl --user restart hermes-gateway
rm -rf /tmp/hermes-agent-abacus-ai
| Variable | Description | Default |
|---|---|---|
ABACUS_AI_API_KEY |
Your Abacus AI RouteLLM API key | — |
ABACUS_AI_BASE_URL |
API base URL | https://routellm.abacus.ai/v1 |
ABACUS_AI_IMAGE_MODEL |
Default image model override | flux2_pro |
image_gen:
provider: abacus_ai
abacus_ai:
model: flux2_pro # default model
| Model ID | Display Name | Best For |
|---|---|---|
nano_banana_pro |
Nano Banana Pro | Highest resolution (up to 4K), Google DeepMind |
flux_pro_ultra |
FLUX Pro Ultra | Highest quality, photorealistic |
flux2_pro |
FLUX 2 Pro | High quality, photorealistic (default) |
flux2 |
FLUX 2 | Fast, good quality |
midjourney |
MidJourney | Artistic, stylistic |
dalle |
DALL-E | Creative, strong prompt adherence |
Once installed and configured, Hermes will use the Abacus AI provider automatically when generating images. Simply ask Hermes to create an image — the image_generate tool will use this provider by default.
Generate an image of a cyberpunk city at night, neon lights, futuristic
Make a photorealistic render of a wooden cabin in the mountains
Create a digital art portrait of a wolf with glowing eyes
hermes chat -q "Generate a beautiful landscape painting of northern lights over a lake"
The provider supports these optional image_config parameters:
| Parameter | Type | Description | Default |
|---|---|---|---|
num_images |
integer | Number of images to generate (1-4) | 1 |
quality |
string | Quality tier (low, medium, high) |
model-dependent |
resolution |
string | Output resolution: 1080p, 2K, or 4K. Only works with nano_banana_pro model. Leave unset for model's default resolution. |
not set (model default) |
rewrite_prompt |
boolean | Auto-improve prompts for better results | true |
Built for Hermes Agent by ZoniBoy00.