Developer Tools / Machine Learning
A hands-on workshop repository that walks developers through building a small GPT-style language model from scratch, including tokenization, transformer blocks, training, and text generation.
The page clearly describes an AI/ML developer project with a concrete learning outcome: writing a GPT training pipeline, training a small model, and generating text. The README shows the workshop structure, model configs, prerequisites, setup steps, and part-by-part coverage, which is enough evidence for a useful public listing.
The snapshot doesn’t show project maturity beyond the README: there are no screenshots, releases, demo outputs, or visible maintenance signals. It also doesn’t show whether the repo includes completed workshop materials, example results, or issue/documentation depth beyond the outline.
Last evaluated 173 days ago. Current rank #1638. Up 249 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.
Lumae is a free native macOS screen recorder and screenshot tool for polished demos, with automatic zooms, cursor smoothing, motion blur, captions, voiceover, and annotated screenshots. It also exposes editing commands over MCP so agents like Claude Code or Claude Desktop can edit projects directly.
A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.
