Hermes Full Stack
Four independent Hermes packs, one licence. The complete stack for autonomous work: typed decision-making, video production, system maintenance, and WordPress shipping.
What's included
- Hermes Decision Brain ($39) — A local-first decision router. 4 of 5 typical decisions answered locally for free, only escalating to the cloud when confidence drops below measured thresholds. Never calls an LLM to decide.
- Hermes Video Automation ($19) — 5 skills that turn a single GPU workstation into an AI video studio. Voice cloning, face animation, lip-sync, FFmpeg assembly. All local, no SaaS.
- Hermes System & DevOps ($19) — 4 skills to keep a workstation fast, free and quiet. Free-model routing, NVIDIA NIM vision fallback, Windows audit, alert silencing.
- Hermes WordPress Automation ($19) — 5 skills to build, maintain and ship WordPress from the terminal. Local provisioning, WP-CLI, backup/restore, SSH deployment.
Why buy the bundle
The four packs cover one continuous workflow: decide what to do, produce the video, keep the machine healthy, ship the client's site. Buying them together saves $17, and it is a single commercial licence — no re-purchase when you move from one part of the toolchain to the next.
Who it's for
Solo developers, indie creators and one-person agencies who want to run an AI-powered workflow end to end on their own hardware, without monthly SaaS subscriptions.
Requirements
- Hermes Agent on Windows, macOS or Linux
- Python 3.11 for the Decision Brain's local runtime (Python 3.8+ for the router itself)
- A CUDA GPU for the Video pack (8 GB VRAM profile included)
- Optional OpenRouter API key (Decision Brain cloud tier, System free-model routing)
Each pack is independent. You do not need all four requirements to use any single pack.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 4 skills unlock instantly in your library.
What's included
4 skillsA local-first decision router that cascades from CPU inference to cloud only when confidence is low.
Turn a single GPU workstation into an AI video studio.
Keep an AI workstation fast, free and quiet.
Build, maintain and ship WordPress from the terminal.
See it in action
Hermes Decision Brain
Example session with this skill installed
Route this user request: "I want to cancel my subscription immediately because of a duplicate charge last month."
Choices: cancel, upgrade, support, billing.
Use auto mode.
- Read your context and instructions
- Compiled the hermes decision brain
Decision successfully resolved using the local tier. The state fit the local token budget and the model answered with enough confidence, so no cloud escalation was needed.
Decision Audit
| Attribute | Value |
|---|---|
| Result | cancel |
| Source | laya (Local, free) |
| Confidence | 0.7402 |
| Escalated | False |
| Latency | 211 ms |
| Cost (USD) | $0.00000 |
| Model | laya-onnx-v1 |
{
"decision": "cancel",
"type": "choice",
"confidence": 0.7402,
"escalated": false,
"escalate_reason": null,
"cost_usd": 0.0,
"latency_ms": 211,
"source": "laya",
"layer_detail": {
"laya": {
"status": "success",
"confidence": 0.7402,
"distribution": [0.7402, 0.0891, 0.1103, 0.0604],
"state_tokens": 68
}
},
"metadata": {
"mode": "auto",
"token_counter": "laya_tokenizer"
}
}
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.