Ask it out loud "what can I earn from this week?" and it reads you back a ranked shortlist - with effort, realistic time to first money, and a ready-to-send message.
Money-relevant opportunities are scattered across places nobody monitors: a bounty posted in a GitHub issue, a hackathon that opens quietly, a paid issue on a job board. Reading them all is unpaid work, so people read none of them. Nemotron Scout is a self-hosted Model Context Protocol server that turns those public signals into a decision.
How it works. Four sources (Devpost, Hacker News, RemoteOK, GitHub issues) are collected in parallel and fail soft, so one dead source never kills a run. An extractor model pulls the money signal out of every item, then a second, more sceptical model argues against it. The survivors are scored, and the best one gets an execution plan: effort estimate, a concrete first hour, explicit kill criteria, and a pitch you can send to the maintainer today.
Why MCP, and why Alexa+. An Alexa+ agent needs a self-hosted MCP server to do real work on the open web. Nemotron Scout speaks standard MCP over Streamable HTTP (protocol version 2025-11-25), with session ids, SSE responses, notifications, resources and ping. scout_voice_answer returns a spoken-ready answer, so a voice agent can drive the whole flow.
The numbers are real. The demo video is an unedited run: 51 items collected across four sources, 6 LLM calls, 13,022 tokens, about 70 seconds wall clock, and zero dollars spent. The top result was a $50 bounty to build a skill that generates a structured CHANGELOG from git history, scored 67.7/100, with a five-step plan and kill criteria.
Runs anywhere. One environment variable swaps the model provider: SCOUT_PROVIDER=openrouter|bedrock|nebius, any OpenAI-compatible endpoint, with a model fallback cascade so a rate limit is never a dead end. It starts on the OpenRouter free tier with NVIDIA Nemotron 3, so there is no paid API key to begin; the demo run used Cerebras gpt-oss-120b through the same OpenAI-compatible path.
MIT licensed, four runtime dependencies, one command to start.
Built With
- amazon-alexa+
- aws-bedrock
- devpost-api
- github-issues-api
- hacker-news-api
- model-context-protocol-(mcp)
- nvidia-nemotron-3
- openrouter
- python
- remoteok-api
- streamable-http
