基于SparkTTS、OrpheusTTS等模型，提供高质量中文语音合成与声音克隆服务。

A local and uncensored AI entity.

Inspect LLM's logprobs and perplexity over a piece of text, or compare two LLMs (like a git diff)

A Slack bot for LLM/ImageGen responses using an OpenAI API backend (LlamaCPP, Ollama, etc)

Dolphin 3.0 🐬: Versatile AI for coding, math, and more

Run Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1, and other state-of-the-art language models locally with scorching-fast performance. Inferno provides an intuitive CLI and an OpenAI/Ollama-compatible API, putting the inferno of AI innovation directly in your hands.

Runpod-LLM provides ready-to-use container scripts for running large language models (LLMs) easily on RunPod.

A genral RAG Search chatbot, with SoTA RAG techniques such as HyDE, Hybrid retrieval with BM25 + RRF and Cross encoder reranking. Evaluated on the BEIR scifact dataset and compared all the different pipelines i tried along the way

The fastest, most efficient library for running GGUF models with maximum throughput and zero-config hardware optimization.

This repository contains concept and code for building AI Agents using langgraph and langchain from absolute basics. These are basic agents built to work with local LLMs.

High-performance Local LLM benchmarking and inference toolkit for Edge CPUs. Features automated profiling for GGUF models, RAM/KV-cache footprint analysis, and optimized llama.cpp execution.

This repository contains concept and code for building Daily use AI Agents using langgraph and langchain from absolute basics. From Straight up browsing the internet to coding applications and debugging code, these AI Agents can be used locally with privacy.

Gemma 3: Google's multimodal, multilingual, long context LLM.

Using Large Language Vision Assistant(Llava) for scene understanding on MetaQuest 3(VR)

FastAPI semantic search + custom entity detection platform.

Simple LLM interface based on terminal + GUI option

Setting up a local inference environment with llama.cpp and pytorch, with CUDA support . Using huggingface transformers and outlines for structured generation.

This repository demonstrates how to use outlines and llama-cpp-python for structured JSON generation with streaming output, integrating llama.cpp for local model inference and outlines for schema-based text generation.