Coding Assistants

OmniRoute keeps your coding agents online by automatically failing over across 177 AI providers—including free tiers—when quotas run dry.

It builds a persistent structural map of your codebase so AI assistants read only the files in a change's blast radius instead of the whole repo.

Orca gives every CLI coding agent its own git worktree so you can run Claude, Codex, and Grok in parallel without stashing or branch juggling.

Pi bundles a unified LLM API, agent runtime, and interactive coding CLI into a monorepo that treats every dependency update as a potential attack.

A curated registry of reusable instruction packages that keep Claude and other agents from reinventing the wheel on every task.

This plugin lets Claude Code users summon OpenAI Codex for read-only reviews, adversarial design critiques, or background task delegation without leaving the chat.

Extracts real design systems from popular websites into markdown files that AI agents read to generate on-brand UI.

A Next.js template that turns AI coding agents into a website reconstruction crew, complete with design-token extraction and parallel worktree builds.

gstack turns Claude Code into a structured engineering team so a single founder can ship like a twenty-person startup without writing most of the code.

Because verbose AI explanations waste tokens and patience, this skill makes agents talk like cavemen—terse, accurate, and cheap.

FastMCP exists because turning a Python function into an LLM-accessible tool shouldn’t require reading a protocol spec.

A local-first, Rust-built AI agent that connects to 15-plus LLM providers and 70-plus tools, now governed by the Linux Foundation instead of a single company.

Impeccable exists to stop AI coding assistants from defaulting to the same handful of SaaS-template tells—Inter everywhere, nested cards, purple gradients—by giving them a curated design vocabulary and 27 deterministic anti-pattern rules.

Reference servers that show how to plug LLMs into files, Git, memory, and time zones—if you read the warning labels first.

A curated directory of Model Context Protocol servers that helps developers discover which AI integrations exist, from databases to browser automation.

Built from scratch in Zig to spare AI agents the cost of hauling around a full Chromium runtime for simple headless tasks.

It strips the telltale signs of AI-generated writing from text, replacing statistical blandness with prose that sounds like it came from a person.

It unifies over a dozen LLM backends into one terminal-first coding agent so you can stop relearning tools every time you switch providers.

A community effort to wrap existing desktop and cloud software in CLI harnesses so AI agents can manipulate real tools—from Blender to Zotero—without native APIs.

Claw Code is an open Rust reimplementation of the Claude Code CLI agent, built by the UltraWorkers community and explicitly not affiliated with Anthropic.