Developer Tool / Machine Learning / LLM Training
A tiny GPT implementation in pure Go, trained on Jules Verne books, with runnable code and notes that explain the model’s evolution and design choices.
The page clearly describes an AI-related developer project: a from-scratch GPT in Go, with instructions to run it, train it on a dataset, and use chat mode after training. The README also adds educational value by walking through the model’s development stages and explaining core transformer concepts.
It’s mainly an educational implementation, so the page does not show production features, benchmark results, supported model sizes, or a polished demo of output quality beyond a few sample lines.
Last evaluated 4 days ago. Current rank #270. Down 6 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.
Browser extension that scans pastes for credentials and PII before they reach LLM chat sites, with local on-device inference and no network calls.
Open-source runtime for multi-agent AI systems with job scheduling, DAG orchestration, shared memory, tool execution, and real-time observability.
