A guide ranking 11 open-source agent harnesses for local LLMs weighs OSI-approved license, documented local runtimes, maintenance status, and safety controls, with repo facts read from GitHub on September 18, 2026. It notes Ollama’s context length defaults depend on VRAM: 4k under 24 GiB, 32k from 24 to 48 GiB, and 256k at 48 GiB or more, while agents and coding tools should get at least 64,000 tokens via OLLAMA_CONTEXT_LENGTH=64000 ollama serve. Goose’s provider docs state models without tool calling can only do chat completion, and Pi’s docs note llama.cpp’s --jinja flag enables compatible chat templates and tool calling. Cline’s local guide maps 16 to 32GB RAM to small quantized models, 32 to 64GB to mid-size coding models, and 64GB or more to larger models; Ollama’s Hermes page lists gemma4 at about 16 GB VRAM and qwen3.6 at about 24 GB VRAM. OpenCode documents Ollama, LM Studio, and llama.cpp’s llama-server local paths, claims support for 75+ providers, recommends at least 64k tokens, and ships build and plan agents. Pi offers read, write, edit, and bash tools, skips MCP, sub-agents, plan mode