freshcrate
Skin:/
Home > #llama-cpp

Tag: #llama-cpp

5 packages â€ĸ ⭐ 1,400 total stars

compose-for-agentsmain@2026-06-04đŸŒŗ Mature⭐922

Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.

DreamServerv2.5.3đŸŒŋ Growing⭐443

Local AI anywhere, for everyone — LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. No cloud, no subscriptions.

cyllama0.3.1🌱 Seedling⭐25

A thin cython wrapper around llama.cpp, whisper.cpp and stable-diffusion.cpp

server-nexev1.0.5-beta🌱 Seedling⭐9

Local AI server with persistent memory, RAG, and multi-backend inference (MLX / llama.cpp / Ollama). Runs entirely on your machine — zero data sent to external services.

MOP0.0.0🌱 Seedling⭐1

A local LLM-based autonomous agent orchestration platform featuring async background tasks, context-isolated sub-agents, dynamic knowledge injection, and strict security approval gates (Plan Mode).