Developer Tool / AI SDK / In-browser LLM inference
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.
The snapshot clearly shows a real AI developer tool with a specific purpose: browser-side LLM inference. It explains how it works, what it supports, and how to install and use it, with examples and model coverage visible. That is enough evidence for a strong public directory listing.
The crawl snapshot does not show setup details beyond package install commands, and the visible text only hints at some advanced features like function calling and custom model flow without showing full implementation limits or configuration steps.
Last evaluated 72 days ago. Current rank #5. Up 161 spots in the rankings.
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.
