Developer Tool / AI Agent Infrastructure
Open-source, self-hostable sandbox for AI agents. It lets agents work inside isolated Linux containers through MCP tools, with CLI and host-level admin controls for creating, managing, and exposing boxes.
The page clearly presents a real AI-powered developer tool with a specific job: giving agents a persistent, isolated Linux sandbox they can control through MCP. The README shows concrete usage, install steps, example commands, supported agents like Cursor and Claude Code, and the architecture of host and in-container MCP servers. It has enough visible product detail to support a useful public listing.
The crawl does not show pricing, hosting requirements beyond a fresh Ubuntu VM, security boundaries in detail, or whether the project is production-ready beyond the demo and quick start. The visible page also truncates before the full command/reference section.
Last evaluated 64 days ago. Current rank #235. Down 4 spots 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.
Mindwalk is a local Go tool that replays Claude Code and Codex sessions on a 3D map of a codebase, showing where an agent searched, read, and edited files over time.
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.
