workflowstacks
local-ai

krasis

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
522 stars+1★ this week33 forksC++Updated 10/22/2026100% free · open source
What it does

Krasis allows you to efficiently run large language models on consumer-grade hardware with limited VRAM, enabling local AI processing without relying on cloud services.

When to use it
  • •When you need to deploy AI models on edge devices or low-end hardware
  • •When you want to keep your AI processing local for security or privacy reasons
  • •When you're working with large language models that exceed the VRAM capacity of your hardware
Ready-to-paste prompt
./krasis -c config.json -p 'What is the meaning of life?'
Heads up: Make sure you have a compatible C++ compiler (e.g., GCC 11 or later) and cmake installed on your system, as Krasis requires a specific build environment to compile and run correctly
Saves to your device
Use with Claude
New

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

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/krasis && curl -fsSL https://workflowstacks.com/api/skills/krasis/claude-skill -o ~/.claude/skills/krasis/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.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

30
top-level files
18
folders
424.8M
source size
Other
license
Key files
README.md
File tree
.github/
assets/
benchmarks/
dist_check/
logs/
perplexity/
podman/
python/
release_inspect/
scripts/
src/
target_prerelease_check/
target_py311/
templates/
testconfigs/
tests/
tools/
vendor/
.gitattributes
.gitignore
ADVANCED.md
build.rs
Cargo.lock
Cargo.toml
Quick Actions
Details
Creator
brontoguana
Language
C++
Category
local-ai
Published
2/9/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/krasis.svg)](https://workflowstacks.com/skills/krasis?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More local-ai tools founders pair with this one.

local-ai★ 132,248
Run Powerful LLMs Locally with llama.cpp – Fast C++ Inference
Empower your product with on‑device LLM inference using llama.cpp’s efficient C++ engine. Ideal for founders who need privacy, speed, and no cloud costs. 130k+ GitHub stars.
local-ai★ 94,887
Stirling-PDF: Edit PDFs Anywhere
Edit PDFs on any device with Stirling-PDF, a tool for startup founders, backed by 80k+ GitHub stars
local-ai★ 38,321
Run AI Locally with llmfit
Find compatible AI models for your hardware with llmfit, a tool for founders, with 29k+ GitHub stars.
local-ai★ 1,061
llama.rn brings LLM power to React Native apps – 1.1k+ stars
Integrate llama.cpp’s large-language-model capabilities directly into iOS and Android via React Native—ideal for founders building AI-enhanced mobile experiences.
local-ai★ 2,439
club-3090
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B
local-ai★ 1,242
crit: Streamline Your AI Agent Feedback Loop
crit lets founders quickly iterate with AI agents via a simple CLI, turning feedback into actionable code improvements. Ideal for Go‑based dev teams. 1.2k+ GitHub stars