llm

Ask Ollama about your local text files

Run, quantize, and fine-tune LLMs on Apple Silicon. Pure Rust, no Python, no CUDA, no ONNX

Preprint: Asymmetry in Low-Rank Adapters of Foundation Models

LangChain, Llama2-Chat, and zero- and few-shot prompting are used to generate synthetic datasets for IR and RAG system evaluation

AI skill for rewriting machine-generated text to sound human-written across 9 languages - 5-stage pipeline: cleanup → specificity → tone → rhythm → proofread.

Build an AI communication analyzer from scratch to understand how AI products actually work. Learn prompt engineering, reasoning pipelines, and local LLM integration using Node.js - no frameworks, no abstractions, just fundamentals

RE:从0开始的RAG学习生活。包含LangChain、LangGraph、LangSmith、PydanticAI等框架和工具的学习教程。

Text Summarization App built using Langchain and Streamlit

Swarms Tools provides a vast array of pre-built tools for your agents, MCP servers, and multi-agent systems.

A modular backend framework for building AI chat applications powered by large language models (LLMs)

Scene-Based Generative Agent

Custom model training using modern architectures. 4-bit QLoRA fine-tuning pipeline for LLaMA 3 8B with production-grade optimization. Memory-efficient training on consumer GPUs. Published adapter on HuggingFace. From training pipeline to deployed model.

This is a fun Python project that allows you to chat with a chatbot about the PDF you uploaded. and generate a PDF transcript of the conversation. The project is built using Python and Streamlit framework.

Claude Skills for connecting Claude.ai to local Weaviate vector databases - manage collections, ingest data, and query with RAG

Agent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRUD, search, hybrid search, full-text search, indexing, RBAC, and common patterns like RAG

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.

[NeurIPS 2025] A multimodal agent that can interact with its own PC in a multimodal manner.

🔥 Alternative to Ollama — multi-model serving with sub-ms model switching · CPU-only 20B inference for Edge AI · llama.cpp + stablediffusion.cpp

Open-source, self-hostable social listening.

Self-hosted PaaS for private infrastructure. Deploy 200+ services on any server in one click. GPU monitoring, AI model management, VRAM checker, and MCP built in. Coolify alternative. MIT licensed. Free forever.