Find secrets with Gitleaks 🔑

Ultrafast serverless GPU inference, sandboxes, and background jobs

LeaderWorkerSet: An API for deploying a group of pods as a unit of replication

CLI for running large numbers of coding agents in parallel with git worktrees

OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)

Finetune LLMs on K8s by using Runbooks

开源的智能体项目 支持6种聊天平台 Onebotv11一对多连接 流式信息 agent 对话keyboard气泡生成 支持10+大模型接口(持续更新) 具有将多种大模型接口转化为带有上下文的通用格式的能力.

Lightweight & fast AI inference proxy for self-hosted LLMs backends like Ollama, LM Studio and others. Designed for speed, simplicity and local-first deployments.

This project allows to launch your Telegram bot in a few minutes to communicate with free or paid AI models via OpenRouter.

Carbon Limiting Auto Tuning for Kubernetes

Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.

WebUI for OpenAI, Ollama and Anthropic

Overengineered telegram bot that functions as a chatbot

An AI agent workflow engine designed for scale

A High-Performance CPU-Based CUDA-Compatible Linear Algebra Library

A tui/cli tool for interfacing with a LLM fine-tuned on various language tasks. It emphasizes on making the user see the changes made in order to learn

Democratizing AI Innovation to the Masses on Commodity Hardware

Llama inference in one pure Go file.

Production-ready AI for Kubernetes. Run cutting‑edge LLMs on NVIDIA GPUs with vLLM. Use Ollama for embeddings and vision. Access securely through OpenWebUI. Scalable, high‑performance, and fully self‑hosted.

This project provides a Kubernetes Operator for managing the lifecycle of the inference-gateway and its related components. It simplifies deployment, configuration, and scaling of the gateway within Kubernetes clusters, enabling seamless integration of inference workflows.