Llama

A curated, auto-generated list of free LLM inference APIs and providers (OpenRouter, Google AI Studio, Groq, HuggingFace, etc.) with their rate...

Hexabot v3 is an AI workflow automation platform that combines YAML-defined workflows, actions, agents, and multi-channel conversational interfaces...

Eagle is a family of frontier vision-language models (VLMs) developed by NVIDIA that combines multimodal understanding with data-centric training...

Operit is a self-contained AI agent and chat application for Android that runs local LLMs (via MNN/llama.cpp) with tool-calling capabilities, memory...

Lemonade is a local AI server that runs optimized LLMs on user GPUs and NPUs (particularly AMD Ryzen AI and Radeon), providing OpenAI-compatible APIs...

RTP-LLM is Alibaba's high-performance LLM inference engine designed for production-scale serving of large language models across multiple business...

llama-swap is a Go-based proxy server that enables hot-swapping between multiple local AI models running on OpenAI/Anthropic-compatible inference...

FastFlowLM is a runtime optimized for running large language models on AMD Ryzen AI NPUs, offering an Ollama-like interface with support for Vision,...

H2O LLM Studio is a no-code GUI framework for fine-tuning large language models (LLMs) without coding experience, supporting techniques like LoRA,...

AirLLM enables efficient inference of very large language models (70B–671B parameters) on consumer-grade GPUs by distributing model layers across...

Wllama is a WebAssembly binding for llama.cpp that enables large language model inference directly in web browsers without requiring a backend...

Strands Agents Tools provides a comprehensive toolkit enabling AI agents to perform practical tasks like file operations, shell execution, web...

TT-NN is a Python and C++ neural network operator library built on TT-Metalium, Tenstorrent's low-level kernel programming model for their custom AI...

AstrBot is an AI agent framework and chatbot platform written in Python that integrates multiple instant messaging platforms (Discord, Telegram, QQ),...

SGLang is a high-performance inference serving framework optimized for large language models and multimodal models, with support for speculative...

Repomix is a tool that converts entire repositories into single, AI-friendly files optimized for consumption by large language models like Claude,...

Claude Code Local enables running Claude Code 100% on-device using local AI models (Qwen 3.5, Llama 3.3, Gemma 4, DeepSeek V4 Flash) on Apple Silicon...

mergekit is a specialized toolkit for merging pre-trained large language models using various algorithms, enabling users to combine model strengths...

vLLM is a high-throughput, memory-efficient inference and serving engine for large language models, using PagedAttention and continuous batching to...

GPUStack is an open-source GPU cluster manager designed for high-performance AI model serving (vLLM, SGLang, TensorRT-LLM) and on-demand GPU instance...

llama.vscode is a VS Code extension that provides local LLM-assisted code completion and agentic coding capabilities powered by llama.cpp. It serves...

ms-swift is a comprehensive fine-tuning and deployment framework for 600+ large language models and 300+ multimodal models, supporting training...

MedicalGPT is a specialized framework for training domain-specific medical language models using multiple optimization techniques (pretraining, SFT,...

An interactive 12-chapter textbook that teaches how to build a modern LLM (GPT/LLaMA-style) from scratch using 7,500+ lines of fully commented code....

PapersGPT is a Zotero plugin that integrates multiple LLM providers (ChatGPT, Claude, Gemini, DeepSeek, and others) to enable AI-powered analysis of...

This is a collection of Jupyter notebooks and code examples for fine-tuning large language models using PEFT (Parameter-Efficient Fine-Tuning) and...

llama.vim is a Vim plugin that integrates local LLM inference via llama.cpp to provide code and text completion directly in the editor. It supports...

LangChain4j is an idiomatic Java library for building LLM-powered applications on the JVM, providing unified APIs across 20+ language model providers...

node-llama-cpp provides Node.js bindings for running large language models locally using llama.cpp, with support for GPU acceleration (Metal, CUDA,...

This is a curated index of Large Language Model resources, covering multimodal generation, agents, code assistance, peer review automation, data...