---
id: "lib-2026-11-05-create-your-own-work-stack-deploying-self-hosted"
type: "library"
title: "Create Your Own Work Stack: Deploying Self-hosted AI and Tooling in a Tech Startup"
lang: "EN"
org: "Grayhat Developers"
source_type: "Practitioner post"
date: "2026-11-05"
week: "2026-W45"
url: "https://nosov.ai/library/lib-2026-11-05-create-your-own-work-stack-deploying-self-hosted/"
original_url: "https://arxiv.org/abs/2611.08116"
tier: "B"
tier_name: "Useful, limited"
tier_reason: "A candid deployment retrospective from a small software firm (Grayhat Developers), accepted as an IAAI-27 poster; the savings are operational estimates with no baseline, by the authors' own account."
summary_basis: "full-text"
original_minutes: "12"
tags: ["ai technology", "enablement", "self hosting", "cost"]
---

# Create Your Own Work Stack: Deploying Self-hosted AI and Tooling in a Tech Startup

Tier B (Useful, limited): A candid deployment retrospective from a small software firm (Grayhat Developers), accepted as an IAAI-27 poster; the savings are operational estimates with no baseline, by the authors' own account.

Summary based on the full text.

## In short

An arXiv paper (5 November 2026) from Grayhat Developers, a software company of under 40 people, on adding self-hosted models next to Claude and Codex. Local models could not replace commercial coding agents: too slow or too weak on repository-level work. They were useful for coordination: pulling context from Outline, Plane and ERPNext into files the coding agents read, and turning agent output into tickets. The first internal rollout failed on setup friction, not model quality.

## Key numbers

- $325: monthly commercial AI spend (Claude and Codex seats plus credits) before local models
- 25.93B+: recorded tokens across those services
- 30-40%: estimated share of commercial AI workload spent on coordination: context transfer, docs and ticket sync
- 27-36%: estimated commercial AI workload displaced by local models, about $88-117 a month
- 8 of 28: version 1 feedback comments about setup and onboarding, the largest category

## What it reports

- Before: seven Claude Team/Claude Code seats (about $175 a month), seven Codex subscriptions (about $140) and about $10 of credits, about $325 a month for over 25.93 billion recorded tokens. Five Claude Pro seats could run out mid-billing period.
- About 20% of a usage window went to documentation sync and a further 10-15% to task and project sync, so 30-40% of workload was coordination.
- Kimi and DeepSeek on consumer hardware were frustrating replacements for complex coding.
- Hybrid set-up: a Gemma model on llama.cpp (RTX 4080 16 GB machine) connected through self-hosted MCP servers to Outline, Plane and ERPNext.
- Version 1 (LobeHub, user-configured) was not adopted; 11 interviews produced 28 comments, 8 on setup and onboarding.
- Version 2 (centrally configured LibreChat with pre-set MCP connectors) improved feedback and use; setup complaints fell from 8 to 3.
- Estimated about 90% of coordination work handled locally, displacing 27-36% of commercial AI workload (about $88-117 a month) against $10-30 a month local running cost.

## How they got it

A first-person retrospective organised around the Kübler-Ross stages. Usage shares come from repeated workflow observation, not token measurement. Feedback counts mix structured interviews (v1) and unstructured Discord feedback (v2).

## Limits

- No formal baseline; several changes happened at once; the authors call the cost figures experience, not evidence.
- Tiny absolute amounts: the savings are about $100 a month, before engineering time and electricity.
- The local/commercial split is manual, not an automated router.

## Why it matters for companies

The split of work is the useful part: frontier agents for hard coding, small local models for context shuffling between internal tools, which is also where internal data is most sensitive. The failure of version 1 is a familiar lesson for any internal AI platform: if staff must configure connectors and authentication themselves, they will not use it. Central configuration mattered more than the model.

Original: https://arxiv.org/abs/2611.08116