AI for more of us. Tom brings local Gemma 4 to everyday Windows PCs, with a light harness, visible actions and local file tools. No dedicated GPU required. Built with GPT-6 Astra. Early beta: browsing and complex tasks still need patience.
WebsiteIQ turns technical, semantic, trust, performance, and machine-readiness checks into inspectable HTML reports with evidence and prioritized fixes without an LLM.
Run a free one-page audit, or let agents quote and buy full-site work
through API, MCP, and x402. A 10-page standard audit costs $0.01, and
white-label output is built in.
Local agent runtime for Gemma 4 on llama.cpp. Unsandboxed by design — code_run is real Python; shell runs against an allowlist. You are the watchdog.
Ships a working jinja template for Gemma 4 (llama.cpp has no built-in one yet) and a GBNF grammar that enforces tool calls at the logit level. 39 tools — semantic memory, browser automation, cron scheduler, and hot-reload skills (the model writes its own). Runs on 7GB VRAM.
MIT, plain Python, no framework dependency.
