Developer Tool / AI Agent / MCP
Open-source football management simulation where AI agents manage a club through MCP while humans watch the action in a terminal TUI. The repo includes a daemon, spectator console, calibration CLI, and detailed setup and command docs.
The page clearly describes an AI-powered project with a concrete workflow: agents interact through MCP, humans watch through a TUI, and the repository documents the daemon, console, calibration tool, quick start commands, and project status. There is enough evidence to understand what it does, how to run it, and why it is relevant to AI builders.
The snapshot does not show screenshots, live demos, or release notes, so a visitor cannot judge the console experience or maturity beyond the written README. It also leaves some product details open, such as which MCP client integrations are supported and how the save/data model behaves in practice.
Last evaluated just now. Current rank #51. Holding steady in the rankings.
WebLLM is a high-performance in-browser LLM inference engine that runs locally in the browser with WebGPU acceleration. It exposes an OpenAI-compatible API, supports streaming and JSON mode, and includes examples for building chat apps and browser extensions.
Self-hosted observability and control plane for production and coding AI agents, with live timelines, fleet-wide feeds, token budgets, MCP allow/block rules, and support for Claude Code plus a Python sensor.
A research prototype for a BitTorrent-style mesh where coding agents share idle capacity, delegate tasks, and settle credits across peers.
