A standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP servers
Run Ornith, Qwen, Nemotron & DeepSeek optimized on AMD Strix Halo — unified OpenAI-compatible server with tuned ROCmFP4 quants, validated 262K context, vision support & hot-swap model zoo (iGPU + NPU)
A fully local OpenCode + llama.cpp + Ornith 1.5 coding-agent setup tuned for 128K context on a tight 6 GB VRAM budget.
Research & experiments running open-source LLMs locally on an 8GB VRAM laptop using Ollama/LM Studio with LangChain integration and performance benchmarks
Privacy-first guide and helper scripts for running Pi with local llama.cpp models on Apple Silicon.
Open models extended to 1M context with YaRN and certified needle by needle: Ornith, Gemma 4 uncensored, Qwen3.6 uncensored. MTP speculative decoding grafts, vision, full test harness.
Add a description, image, and links to the ornith topic page so that developers can more easily learn about it.
To associate your repository with the ornith topic, visit your repo's landing page and select "manage topics."