Alternatives hub · graph-backed
llama.cpp alternatives
Not a popularity vote. Each is a typed edge from llama.cpp with the reason it exists in Inference & Serving - ranked with live GitHub stats, not marketing.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A high-throughput and memory-efficient inference and serving engine for LLMs
CLI proxy reducing LLM token consumption by 60-90%
Unsloth Studio is a web UI for training and running open models locally.
Stop renting your intelligence. Own it with AnythingLLM.
Universal memory layer for AI Agents
Python SDK and Proxy Server for calling over 100 LLM APIs in OpenAI format
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
AI 低代码平台【双重驱动模式】支持快捷开发
Unified framework for scaling AI and Python applications
Langchain-Chatchat is a local knowledge-based RAG and Agent application for LLMs like ChatGLM, Qwen and Llama.
Curriculum for building AI systems from scratch
Your AI second brain. Self-hostable.
《开源大模型食用指南》
SGLang high-performance serving framework
Hundreds of models & providers. One command to find what runs on your hardware.
Data infrastructure for AI
Repository listing free and trial-based LLM inference API resources
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications.
分享大模型技术原理与实战经验，涵盖工程化和应用落地
A large collection of free n8n automation templates
Repository for running large language models with reduced memory usage on limited GPU hardware.
Build multimodal AI applications with cloud-native stack
Reference stack for running AI agents securely in OpenShell