Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for local-LLM users, AI agent builders, and developer-tools engineers who need an MIT-licensed, open-source local-first AI assistant with a Node.js + TypeScript core, a TUI, Playwright-driven browser automation, llama.cpp / GGUF model support, and a claimed 69.8% GAIA L1 score (vs 58.5% for Hermes), so they can run an OSS local-first agent stack that combines CLI + browser automation + a He
Who should use it
Who should skip it
Skip if the source link, docs, or setup requirements do not match your workflow.
Risk explanation
It is an MIT-licensed local-first AI assistant that bundles Playwright-driven browser automation on top of a local llama.cpp / GGUF model, so review which browser sessions and authenticated cookies the assistant is allowed to access, scope which local model checkpoints it can load, confirm that the TUI endpoint is bound to localhost before exposing it externally, and gate any production rollout behind a security review before granting the browser-automation layer access to authenticated sessions.