llama-server

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command. No Electron, no Python, offline-first.

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

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models

1-Click LLM Server on Your Phone — no Termux needed! 无需Termux，一键让你的手机变成LLM服务器！

Lightweight proxy for LLM

A lightweight chat terminal-interface for llama.cpp server written in C++ with many features and windows/linux support.

Run Pi coding agent isolated in a Docker Sandbox microVM with a local llama-server as the inference backend

BoxedLLaMA is a specialized software toolkit designed for developers to integrate local artificial intelligence into Windows applications. It functions as a comprehensive wrapper for llama.cpp, automating complex tasks such as server installation, version updates, and model management from Hugging Face.

CLI wrapper for llama.cpp providing an ollama-like experience

Local LLM proxy, DevOps friendly

大模型推理服务性能调优

A robust, production-ready Python toolkit to automate the synchronization between a directory of .gguf model files and a llama-swap config.yaml

∿ Py-Agent · Local-First & Private harness optimized for small models with self-healing tool adapters.

One place to store and manage all your recipe for Llama Server

FastAPI proxy that strips volatile fields from OpenClaw requests to dramatically improve llama-server KV cache hit rates (~22× faster prompt eval)

OpenCode TUI plugin for fuzzy and semantic search across local conversation and session history

A standalone, all-on-by-default token-optimization + memory layer for LLM requests: minifies tools/system/messages (code-fence aware), dedups tool results, distills old turns, prunes to a budget, type-compresses output; hot/warm/cold memory manager with atomic writes. Async proxy for Anthropic, OpenAI & Ollama + MCP server (stdio) + CLI. MIT.

为DSH接入本地大模型能力：在「设置→插件」页一键启停本地 llama.cpp 大模型（双槽x双模态x双预设），卡片内配置、一条命令安装、自动注册，装完即用| Enable local large model capabilities for DSH: One-click start/stop for local llama.cpp models (dual‑slot × dual‑modal × dual‑preset) right in Settings → Plugins; configure within the card, install with a single command, automatically register, and ready to use

llama.cpp instance manager — spin up GGUF models with a web UI, REST API, and full flag control. Pull from HuggingFace, chat, manage instances from browser or CLI.

Profile-based launcher for local LLM servers - start, stop and switch models on llama.cpp, Ollama and LM Studio from one CLI/TUI. Zero resident overhead, optional MCP control plane, importable as a Go library.