FILE NO. 0001-OS · MMXXVI★ UNLIMITED · ON DUTY 24/7
★ Veteran-owned Columbus, Ohio 39°57′N · 82°59′W

Your AIisn't broken.It's uninstalled.

I install, configure, and teach you how to actually use every major AI agent — OpenAI, Codex, Claude Code, Claude Co-Work, OpenClaw, Gemini CLI, Gemini Agent, voice agents, and custom builds. Unlimited usage. Unlimited agents. Over the phone, over screen-share, or in person.

NNEESESSWWNW39.9612°N · 82.9988°W
OPENAI
CODEX
CLAUDE CODE
CLAUDE CO-WORK
OPENCLAW
GEMINI CLI
GEMINI AGENT
HERMES AI
AGENT SDK
MCP SERVERS
VOICE AGENTS
CUSTOM AGENTS
MOBILE APPS
CRYPTO AGENTS
UNLIMITED
24/7
OPENAI
CODEX
CLAUDE CODE
CLAUDE CO-WORK
OPENCLAW
GEMINI CLI
GEMINI AGENT
HERMES AI
AGENT SDK
MCP SERVERS
VOICE AGENTS
CUSTOM AGENTS
MOBILE APPS
CRYPTO AGENTS
UNLIMITED
24/7
01 · UNLIMITED

Unlimited agents

Set up as many agents as you need. OpenAI, Codex, Claude Code, Claude Co-Work, OpenClaw, Gemini CLI, Gemini Agent, voice receptionists, custom builds — wired together, running on your accounts. No per-seat cap on what I'll install.

02 · PRICING

Price over the phone

We talk scope on a free call or video, and you get a flat number before anything starts. No hourly trickle, no AI-consultant markup, no surprises on the invoice. If a job isn't a fit, I'll say so.

03 · AVAILABILITY

On-call 24 / 7

Call, text, video, screen-share, or I drive to you. If you need something right away, call or text any time. I handle everything on my end so you don't have to learn the terminal to get value.

~80%
Of small & mid-size businesses · Have not deployed a single AI agent
The gap

Most businesses aren't behind.
They just haven't been shown.

The agents that move work — Claude Code on a real repo, a voice agent answering after-hours calls, an SDK-based assistant wired into your tools — aren't difficult because the tech is hard. They're difficult because nobody sits with you long enough to make them yours.

That's the entire job. I sit with you. We get it running on your machine, on your accounts, with your data. Then I make sure you can drive it without me.

References: SMB AI adoption surveys 2024–25 · McKinsey State of AI · author's field installs
ROI · Time saved · By industry

What this actually returns.

Real published numbers from 2024–2026 studies — not made up. Your business will land somewhere on these ranges depending on where you start. I size the install to the result, not the hype.

VERTICAL 01OS·ROI—001
LAW · ACCOUNTING · PROFESSIONAL SVC
6–10 hrs / wk
≈ $6,500 – $19,500 / yr per knowledge worker

Document review, drafting, intake summaries. Tech.co (2025) finds 22% of SMB leaders save 6–10 hrs/week with AI; HubSpot State of Marketing pegs content work at 5–15 hrs/wk saved.

STACK · Claude Code + Codex + Hermes orchestration
VERTICAL 02OS·ROI—002
HVAC · PLUMBING · ELECTRICAL · TRADES
20 – 40 hrs / mo
$500 – $2,000 / mo direct savings

After-hours call capture, booking, dispatch triage. Forbes / SMB Group (2024): 66% of SMBs say AI saves between $500–$2,000 per month, most often on customer-facing intake.

STACK · Voice receptionist + Gemini Agent + CRM
VERTICAL 03OS·ROI—003
MARKETING · CREATIVE · AGENCIES
5 – 15 hrs / wk
30 – 40% time cut on content within 60 days

Email, social, ad copy, briefs. HubSpot State of Marketing 2025 — small businesses report 5–15 hrs/wk saved on content; most see 30–40% reductions in content time inside two months.

STACK · OpenAI + Claude Co-Work + custom workflows
VERTICAL 04OS·ROI—004
RETAIL · E-COM · LOCAL SERVICE
40 – 60% of inquiries automated
Up to 30% lower operating cost

Order status, returns, scheduling, basic Q&A. Thryv (2025) finds AI can cut operating cost up to 30% when applied to high-volume manual work; chatbots handle 40–60% of routine inquiries.

STACK · OpenAI chatbot + voice agent + Shopify/Square
VERTICAL 05OS·ROI—005
GENERAL CONTRACTORS · FIELD OPS
5 – 7 hrs / wk per manager
1.8× more likely to report YoY revenue growth

Estimates, scheduling, takeoffs, vendor email. Business.com 2026 SMB AI Outlook: managers save 7.2 hrs/wk on average; Capsule/SMB Group: AI-investing SMBs nearly twice as likely to report revenue growth.

STACK · Custom app + Codex + Gemini CLI tooling
VERTICAL 06OS·ROI—006
SOFTWARE · STARTUPS · INTERNAL TOOLS
23 – 33% productivity uplift
Real measured developer throughput

Repo work, PR drafts, test gen, incident triage. Goldman Sachs (2026, citing academic studies + company anecdotes): 23% avg productivity uplift, ~33% in deployed efficiency gains.

STACK · Claude Code + Codex + Agent SDK
★ SOURCES · Tech.co SMB AI Survey 2025 · Business.com 2026 SMB AI Outlook · HubSpot State of Marketing 2025 · Forbes / SMB Group 2024 · Thryv SMB AI Report 2025 · McKinsey State of AI 2024–2025 · Goldman Sachs 2026 productivity brief · Capsule CRM SMB stats 2026.
Ranges are industry baselines. Your number lands on this curve based on team size, current tool stack, and how much manual work you're doing today. I'll size it on the discovery call.
Agents I install

Every major AI agent. Installed, wired, explained.

AGENT 01OS—001

OpenAI · GPT, ChatGPT Business & API

Workspace setup, custom GPTs, API keys with sane budgets, project folders, and a real prompt library tuned to how your team writes. Live walk-through of every part you'll actually use.

LOG · OPENAI: gpt · projects · custom-gpts · api · budgets
AGENT 02OS—002

Codex — OpenAI's coding agent

Install, repo connect, sandbox config, review workflow. I run it through a real ticket from your backlog so you see the loop end-to-end before I hand off.

LOG · CODEX: repo-connect · sandbox · review-loop · ship
AGENT 03OS—003

Claude Code · Claude Co-Work · Agent SDK

The Anthropic stack: Claude Code as your agentic IDE, Claude Co-Work for team workflows, and the Agent SDK when you need a custom worker. MCP servers, sub-agents, slash commands, the works.

LOG · CLAUDE: code · co-work · sdk · MCP · sub-agents
AGENT 04OS—004

OpenClaw — open-source autonomous agent

Open-source agent runtime, installed on your hardware, wired to your tools. No vendor lock-in. I configure the workers, run them through a live task, then teach you to extend them.

LOG · OPENCLAW: self-hosted · workers · tools · open-source
AGENT 05OS—005

Gemini CLI & Gemini Agent (Google)

Google's command-line agent and the broader Gemini agent stack. Auth, tooling, model selection, and live use against your real workload. Bring-your-own-Workspace friendly.

LOG · GEMINI: cli · agent · workspace · grounded · live
AGENT 06OS—006

AI phone receptionists & voice agents

After-hours line that books appointments, answers FAQs, qualifies leads, routes urgents. Real voice, real phone number, your script. Live in a week.

LOG · VOICE: 24/7 · routing · CRM-aware · SMS fallback
AGENT 07OS—007

Custom apps & websites — for any business

Built the same way your competitors hire a five-person agency for, in a fraction of the time. Modern stack, modern design, modern AI baked in from day one.

LOG · BUILD: next · supabase · stripe · agentic from day-one
AGENT 08OS—008

Mobile apps — iOS & Android

Native-feeling mobile apps for your business or your customers. React Native or Expo, App Store + Play Store submission handled, push notifications, deep links, agents baked in. From idea to shipped in weeks, not quarters.

LOG · MOBILE: ios · android · push · store-submit · agentic
AGENT 09OS—009

Hermes AI Agent + custom orchestration

An autonomous research / ops worker wired to your stack, plus the orchestration layer that lets your other agents talk to each other. One control plane, not ten browser tabs.

LOG · HERMES: research · ops · orchestration · routing
AGENT 10OS—010

Custom skills, tools & plug-ins

Custom Claude Skills, ChatGPT tools, function-calling endpoints, and plug-ins that teach your agents how to do the specific things your business actually does. Built, tested, documented.

LOG · SKILLS: claude-skills · gpt-tools · function-calls · docs
AGENT 11OS—011

Apps, GPTs & marketplace listings

Internal apps, ChatGPT custom GPTs, Claude Apps, Workspace add-ons — and, if you want, listed on the public marketplaces so the public can find you. Yours, branded, your data.

LOG · APPS: custom-gpts · claude-apps · workspace · listed
AGENT 12OS—012

Connectors & integrations

Your agents plugged into the tools you already run — CRM, email, calendar, Stripe, Shopify, QuickBooks, Notion, Slack, HubSpot, Airtable, your database. OAuth, webhooks, retries, the boring parts done right.

LOG · CONNECT: oauth · webhooks · zapier · make · n8n · native
AGENT 13OS—013

MCP servers — Model Context Protocol

Custom MCP servers that expose your tools, files, and databases to Claude, Cursor, and any MCP-aware client. Hosted or self-hosted, auth-gated, with clean schemas. The standard your agents will speak next year.

LOG · MCP: server · tools · resources · auth · hosted/self
AGENT 14OS—014

Crypto trading systems

Quant-style systems on the exchanges you already use — Coinbase, Kraken, Binance, Bybit, on-chain via Hyperliquid or GMX. Backtests, risk caps, kill-switch, paper-trade phase before a dollar is live. I install, you control the keys.

LOG · QUANT: backtest · paper · risk-caps · live · kill-switch
AGENT 15OS—015

Crypto trading agents

Autonomous agents that read the book, the news, on-chain flow, and your rules — then act inside the limits you set. Strategy + signal + execution + reporting, all in your wallet, all in your control.

LOG · AGENT: signal · execute · report · within-your-rules
AGENT 16OS—016

Custom automated workflows

End-to-end automations that run while you sleep — intake to invoice, lead to follow-up, ticket to resolution. Triggered by email, webhook, schedule, voice, or your CRM. Failure alerts and logs included, no 'it stopped working last Tuesday' mystery.

LOG · FLOW: trigger · act · log · alert · retry
AGENT 17OS—017

Custom agents — built for your business

When nothing off-the-shelf fits, I build one. Custom prompt, custom tools, custom memory, custom guardrails. Trained on your docs, plugged into your stack, branded as yours. From a single specialist to a small team of agents that hand off to each other.

LOG · CUSTOM: prompt · tools · memory · guardrails · yours
AGENT 18OS—018

1-on-1 AI training & ongoing support

Anything you want to learn — how to prompt, how to chain agents, how to read a terminal log, what's worth your time, what's a fad. By the hour, by the project, or on a flat monthly retainer.

LOG · TRAIN: live · screen-share · recorded · transcribed
How I work

Four steps. No mystery.

STEP 0101

Reach out — any channel

Phone, text, email, the form below. I answer the same day, usually within an hour. Tell me what you're trying to do — agents, automations, voice line, whole new site — and we go from there.

DAY 0≤1 HR
STEP 0202

Free 20-minute discovery call

We map what's worth doing, what isn't, what the install will actually look like on your setup. You get a flat quote, a timeline, and a written scope before you commit anything.

DAY 020 MIN
STEP 0303

Install — phone, screen-share, or on-site

I work alongside you while it goes in. You watch every step. You keep the credentials. By the time we hang up the agents are running on your machine, on your accounts, doing real work.

DAY 1–51–5 DAYS
STEP 0404

Training, handoff, ongoing support

Live walk-through, recorded session, written runbook. Then you're independent — but I'm a phone call away. Monthly retainer if you want me on call; pay-as-you-go if you don't.

DAY 5+ONGOING
SCOPE · OS—2026
What I won't take on

Where I draw the line.

  • Anyone asking me to build something illegal, deceptive, or designed to harm a third party
  • Spam, scrape-and-republish, fake-engagement, or anything that violates a platform's ToS
  • "Just give me your API key and run my whole life" — I install your stack, on your accounts, in front of you
  • Crypto: I'll talk to you about it, I'll build trading agents or on-chain tooling, but I do not give financial advice
If a job isn't a fit I'll tell you on the discovery call. Often I can point you at someone who is.
Jeremy Gephart, founder of OpenStar AI Agents
★ OS—2026 · ARCHIVE
The operator

I'm the guy who picks up
when the agent breaks.

Eight years in the Army taught me how to make systems work in places they weren't supposed to. I've spent the last few years doing the same with AI — every agent, every SDK, every weird local install, every terminal trick.

OpenStar AI Agents is the version of that I sell to other people. Phone calls at 2 AM, screen-shares with a small-business owner, a custom build for an enterprise team, a one-hour training for someone who just wants to understand what all this is. Same operator either way.

If you've been told AI is going to be hard for your business — it isn't. It just hasn't been installed yet, and nobody has sat down with you long enough to make it yours. That's the whole job.

— J. Gephart
JEREMY GEPHARTFOUNDER · U.S. ARMY VETERAN
COLUMBUS · OHIO · MMXXVI
Recent installs · Anonymized

Real work, quietly delivered.

Live · Client identifiers withheld
OS—0418
CLAUDE CODE
law firm · agentic doc review pipeline · 4 MCP servers
Shipped
11 DAYS AGO
OS—0417
VOICE AGENT
hvac company · after-hours intake + booking · live
Shipped
14 DAYS AGO
OS—0416
GEMINI AGENT
marketing agency · autonomous research worker
Training
17 DAYS AGO
OS—0415
CUSTOM BUILD
general contractor · estimate-gen app · stripe wired
Shipped
21 DAYS AGO
OS—0414
CODEX
saas team · codex on monorepo · review pipeline
Shipped
25 DAYS AGO
OS—0413
CLAUDE CO-WORK
accounting firm · team workflows · 12 seats wired
Shipped
27 DAYS AGO
OS—0412
OPENCLAW
local retailer · self-hosted agent on shopify
Training
29 DAYS AGO
OS—0411
OPENAI / GPT
realtor team · custom gpts + api budgets + training
Shipped
32 DAYS AGO
OS—0410
TRAINING
founder cohort · 6 sessions · prompt + agent chain
Shipped
34 DAYS AGO
★ ALL ENGAGEMENTS ANONYMIZED · CLIENT NAMES NEVER DISCLOSEDOS · MMXXVI · COLUMBUS, OH
Questions

Frequently asked.

Price is by scope and we discuss it on a free phone or video call. You get a flat number in writing before I start — not an hourly meter. Smaller jobs (single-agent setup + training) usually run a few hundred dollars; full stacks with Claude Code + Codex + Gemini + voice agent are in the low thousands. No surprises on the invoice.
On a single engagement I'll wire up as many agents as your business actually needs — OpenAI, Codex, Claude Code, Claude Co-Work, OpenClaw, Gemini CLI, Gemini Agent, a voice receptionist, a custom internal app — with no per-seat or per-agent surcharge from me. You're only paying the underlying model providers' fees, which we right-size during install.
Same day if you call. Most discovery calls happen within an hour of you reaching out. Installs start within 24–48 hours of you saying go. If you need something right away, feel free to call or text the number on this page any time — 24/7 isn't a slogan, it's how I work.
Either. Most of my work is over phone, video, and screen-share — same outcome, faster, cheaper for you. If you're near Columbus and want me in the room, that's an option too. I handle everything on my end either way.
All the numbers in the ROI section are from published 2024–2026 research — Tech.co, Business.com, HubSpot State of Marketing, Forbes / SMB Group, Thryv, McKinsey State of AI, Goldman Sachs. I'm not making them up. Your number will land on those ranges depending on team size and current manual workload, and I'll size the install to land you there.
Most of my clients are non-technical. The training half of the job is built for you specifically. By the end you'll know what's running, why it's running, and how to use it — without needing me to come back.
Either pay-as-you-go (call me when something breaks) or a monthly retainer if you want me on call. I'm available 24/7 either way — the retainer just locks in priority and a flat rate.
★ Discovery call

Twenty free minutes.
Tell me what you're trying to do.