93+ production-ready AI projects with tutorials on LLMs, RAG, and agents.
ollama-herd
Open sourceLocal AI load balancer for Ollama and MLX fleets with auto-discovery, smart routing, and OpenAI-compatible API.
Local AI load balancer for Ollama and MLX fleets. Auto-discovery, smart routing, OpenAI-compatible API, zero config. Perfect for Mac Minis & Studios.
Pros
- +Zero-config mDNS auto-discovery across devices
- +Smart routing with thermal, memory, and latency awareness
- +Supports multimodal models: vision, image gen, speech-to-text
- +OpenAI-compatible API for easy integration
Cons
- −Requires multiple devices for full benefit
- −Homebrew install can take ~25 minutes due to source builds
- −Limited to local network; no cloud scaling
Target audience: Developers and homelab enthusiasts running local AI fleets on Mac Minis or Studios who want to pool compute without cloud costs.
Related tools
Other open-source tools that share tags with ollama-herd.
QwenPaw
QwenPaw: Your personal AI assistant, deployable locally or in the cloud, with memory, multi-agent support, and multi-cha
Alternative to
Horizon
AI-powered news radar generating daily bilingual briefings in English & Chinese.
Intelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI with semantic caching and auto-failover.
Alternative to
granitepi-4-nano
Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device
crawl4ai
Open-source web crawler that turns any website into clean, LLM-ready Markdown for RAG and AI agents.
Alternative to