Scout.

agent online · wikipedia tools · gemini-class reasoning on the edge

A real research agent: give it a question and it plans, searches Wikipedia, reads pages and writes you a sourced brief — every thought and tool call streams live as it happens.

no api keys no accounts free hosting · free inference fully streamed

Brief the agent

how do noise-cancelling headphones work?
what is the chola dynasty's contribution to south indian temple architecture?
why do we dream?
how did the konkan railway change mangaluru?

The agent loop

idle
idle
brief the agent — every thought, tool call and observation will appear here, live.

How it works

This is the real agentic loop: the LLM on Cloudflare's edge responds with a strict JSON action — {"thought": "…", "action": {"tool": "search", "args": {…}}} — the server executes the tool against Wikipedia's public APIs, and the observation is fed back into the model's context. Repeat until the agent calls finish with a sourced brief, or hits the 9-step limit — where a forced synthesis pass writes the brief from everything gathered, so you always get an answer.

The whole loop streams as server-sent events. Inference runs on Workers AI's free tier — no API keys in your browser, nothing to pay. If the model breaks the JSON protocol, the server sends an automatic repair prompt and continues.