SkywardAI/kirin
Self-hosted and local-first application for inference and RAG on consumer grade hardware.
This tool helps you set up a private, local-first AI assistant for question-answering on your own documents and data, all on standard computer hardware. You feed it your text-based datasets, and it allows multiple users to chat with a small AI model, saving and sharing their conversation history. It's for businesses or individuals who need to process sensitive information securely without sending it to third-party cloud AI services.
No commits in the last 6 months.
Use this if you need a self-hosted, private AI chatbot for your organization's internal data, running on readily available hardware like a desktop computer with a decent CPU.
Not ideal if you need to train large, complex AI models from scratch, as this tool is focused on inference and RAG with pre-processed datasets, not extensive model development or large-scale training.
Stars
6
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/SkywardAI/kirin"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
parthsarthi03/raptor
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
ENDEVSOLS/Long-Trainer
Production-ready RAG framework for Python — multi-tenant chatbots with streaming, tool calling,...
viddexa/autollm
Ship RAG based LLM web apps in seconds.
Neverdecel/CodeRAG
CodeRAG is an AI-powered tool for real-time codebase querying and augmentation using OpenAI and...
pierreolivierbonin/Canada-Labour-Research-Assistant
The Canada Labour Research Assistant (CLaRA) is a privacy-first LLM-powered RAG AI assistant...