ai-agent

awesome-local-llm – Launch Self‑Hosted LLMs Faster with 2.9k+ Stars

Name: awesome-local-llm – Launch Self‑Hosted LLMs Faster with 2.9k+ Stars
Author: rafska

A founder‑focused collection of platforms, tools, and best practices for running large language models on‑premise. Ideal for startups needing privacy‑first AI without cloud costs.

From the repo · “A curated list of awesome platforms, tools, practices and resources that helps run LLMs locally”

2,979 stars+57★ this week474 forksGuide quality 9/10 · reviewed Oct 4Updated 10/17/2026100% free · open source

What it does

Awesome-local-llm provides a curated list of resources and tools to help founders self-host and run large language models (LLMs) locally.

When to use it

•When you need to deploy AI models on-premises due to data privacy concerns
•When you want to reduce cloud costs by running AI workloads locally
•When you need more control over the AI infrastructure and model updates

Ready-to-paste prompt

To get started with a specific LLM platform, for example, Docker, paste the command `docker run -it --rm rafsk/llm-local` to run a local LLM instance

Heads up: Make sure you have Git installed on your system and configured properly to clone the repository, as some resources may require Git for deployment or setup

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/awesome-local-llm && curl -fsSL https://workflowstacks.com/api/skills/awesome-local-llm/claude-skill -o ~/.claude/skills/awesome-local-llm/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How awesome-local-llm – Launch Self‑Hosted LLMs Faster with 2.9k+ Stars works

Codeflow

Free to inspect

Awesome-local-llm – Launch Self‑Hosted LLMs Faster with 2.9k+ Stars is a documents-only repository (2 doc files) — something you read, not something you run. There is nothing to install. Last commit this month, MIT license.

Size

Documents only

2 documents · 18 min skim

Setup

Nothing to install

A guide / curated list. Just read it and follow the links.

Runs on

Nowhere — you read it

A reading resource, not a program.

Where to start reading

1
README.md
Start here — what it does and how to install it

READMEMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/awesome-local-llm && curl -fsSL https://workflowstacks.com/api/skills/awesome-local-llm/claude-skill -o ~/.claude/skills/awesome-local-llm/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

rafska

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.