large-language-models

Ultrafast serverless GPU inference, sandboxes, and background jobs

🏗️ Fine-tune, build, and deploy open-source LLMs easily!

A holistic way of understanding how Llama and its components run in practice, with code and detailed documentation.

[deprecated] AI Gateway - core infrastructure stack for building production-ready AI Applications

A diverse, simple, and secure all-in-one LLMOps platform

A super handy instant messaging app that mixes microservices with AI big models, loaded with features and all about speed and security.

Implement RAG (using LangChain and PostgreSQL) for Go applications to improve the accuracy and relevance of LLM outputs

Interactive Fiction in the Age of AI

An AI assisted kubectl helper

Go package and example utilities for using Ollama / LLMs

AWS Go SDK examples for Amazon Bedrock

Type-safe AI agents for Go. Suricata combines LLM intelligence with Go’s strong typing, declarative YAML specs, and code generation to build safe, maintainable, and production-ready AI agents.

GLM-5.2 NVIDIA NIM Go 客户端 / OpenAI 兼容反向代理 — 自动化 hCaptcha 凭证池 + 流式推理，支持 Docker 部署。Go client & OpenAI-compatible proxy for NVIDIA Playground's GLM-5.2, with hCaptcha automation, captcha pool, streaming, and Docker.

Inference Llama 2 in one file of pure go

A simple Read-It-Later and link collection tool, AI-powered for text and images, multi-platform, open-source. A browser extension available for one-click bookmarking. My undergraduate thesis at HUST.

Go framework for language model-powered applications with composability and chaining. Inspired by LangChain.

LLM Prompt Injection Detection API Service PoC.

With an emphasis on pluggable architecture and platform flexibility, Thor is a highly modular chat engine integrated into Go.

🧠 Cache implementation for storing and retrieving results of language model (LLM) requests

This repository is a work in progress (WIP).