GrokBoy

Minimal local GrokBot-like CLI agent. Phase P3: optional Playwright DOM browser tools.

Status

Phase	Status
P0 streaming chat	done
P1 shell / files + ReAct	done
P2 completion / loop guard / truncation	done
P3 browser (Playwright DOM)	done (optional)

No Docker desktop, no Codex/LazyBoy fork.

Setup (macOS)

export GROKBOY_API_KEY=your_key   # or XAI_API_KEY
# optional:
# export GROKBOY_BASE_URL=https://api.x.ai/v1
# export GROKBOY_MODEL=grok-4.6
# export GROKBOY_CONTEXT_CHARS=100000

cd ~/GrokBoy
cargo run -p grokboy -- chat

Optional: Playwright browser tools

Browser tools are always registered but fail closed until you install the helper:

cd ~/GrokBoy/tools/playwright
npm install
npx playwright install chromium

Then the agent can use browser_navigate, browser_snapshot, browser_click, browser_type, browser_eval (DOM/selector/role — not screenshot-first).

Commands

• grokboy chat — interactive streaming chat (no tools)
• grokboy run "<prompt>" — one-shot agent with tools
• grokboy run --session <id> "<prompt>" — continue a saved session
• grokboy smoke — offline checks (no API key / no Chromium required)
• grokboy help

Tools: shell, list_dir, read_file, write_file, report_done, report_blocked, browser_navigate, browser_snapshot, browser_click, browser_type, browser_eval.

Sessions are stored under ~/.grokboy/sessions/<id>.json (may include last_browser_url).

The agent stops on report_done / report_blocked, blocks identical tool rounds (×3), and truncates old context when over budget.

繁體中文

本機終端機 coding assistant。P3 可選 Playwright DOM 瀏覽器工具（非截圖優先）。

export GROKBOY_API_KEY=你的金鑰
cd ~/GrokBoy
cargo run -p grokboy -- smoke
# 可選瀏覽器：
cd tools/playwright && npm install && npx playwright install chromium
cargo run -p grokboy -- run "打開 example.com 並 snapshot"
cargo run -p grokboy -- chat

Layout

crates/grokboy-core/   # config, model, tools, browser, agent, session
crates/grokboy/        # CLI binary
tools/playwright/      # optional Node Playwright helper (JSONL)
docs/ACCEPTANCE.md