Installation

Install

hara is a Node CLI (Node 20+), published as @nanhara/hara.

npm i -g @nanhara/hara
hara --version

Pick a model

hara works with any provider — Anthropic Claude, Qwen (free OAuth tier), GLM, or any OpenAI-compatible endpoint (including a local model).

# Qwen (free): device login
hara login qwen
 
# …or any provider via env / config
export ANTHROPIC_API_KEY=sk-...
hara config set provider anthropic
hara config set model claude-opus-4-8

First run

Point hara at a project and talk to it in the TUI:

cd your-project
hara                 # interactive REPL
# or one-shot, headless:
hara -p "fix the null check in src/login.ts and run the tests"

hara doctor checks your provider, auth, model, roles, skills, and memory if anything looks off.