Local-first quickstart
Install ONE with Python 3.12 or newer:
python3 -m pip install one-agentone --versionStart an Ollama server separately, with a model available, then choose its actual
model name in place of MODEL_NAME:
one --provider ollama --model MODEL_NAME --ollama-url http://localhost:11434/v1Ask it to explain a small repository. Alternatively, use a local llama.cpp
server with --provider llama.cpp --model MODEL_NAME --llama-cpp-url http://127.0.0.1:8080.
These local providers do not require an API key; they still require a running,
compatible server and model. ONE can execute tools with your permissions: use
--preset readonly --no-extensions --no-mcp for a more restricted inspection,
not as an OS or network sandbox.
Local state is stored under ~/.config/one by default, not necessarily inside
the current repository. See configuration,
CLI reference, and presets.