GitHub Trending weekly on October 28, 2026

An orchestration desktop for running many coding agents in parallel git worktrees, with phone monitoring and remote execution.

Builds a local, queryable knowledge graph of a codebase so coding agents can navigate it instead of grepping.

A design vocabulary and linting skill set that steers coding agents toward better UI and catches generic AI design patterns.

A multi-agent LLM framework that debates and decides stock trades, for researchers and quant-curious developers.

An MIT-licensed terminal coding agent for developers who want full control over model choice and local file access.

A CLAUDE.md rule set for coding agents that pushes them to ask before assuming, keep diffs small, and work toward verifiable goals.

Agent skill that pushes coding agents toward directed, image-backed web pages and catches generic AI layouts in a real browser.

A Claude Code skill that audits websites for technical SEO, structured data, and AI-search readiness.

Role-specific Claude Cowork plugins that give non-engineers prebuilt skills, commands and tool connectors for their job function.

A harness that wraps Claude Code and Codex with swarms, persistent memory, and cross-machine federation for multi-agent work.

Shared long-term memory for coding agents so you can switch harnesses or machines mid-task without re-explaining context.

Control Claude Code, Codex and other coding agents from a local server, web app, desktop app or phone.

A Python web framework that turns type hints into validated, self-documenting REST APIs for backend developers.

Official Android skill files that teach coding agents how to handle Android tasks LLMs usually get wrong.

Agent skills that give coding assistants concrete rules for reviewing and building UI, typography, color, accessibility and interface copy.