Loading...
Loading...
Pilot Shell: Professional context and harness engineering for Claude Code and OpenAI Codex. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Pilot Shell. This is an automatic list. We have not written a researched verdict for Pilot Shell yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified.
Claude Code Skills is an open source library of skills for Claude Code and Codex, maintained by independent product engineer Lev Berezhnoy. Each skill turns a recurring lesson from working with AI agents into reusable guidance that gives the agent a concrete outcome, a way of working and completion criteria, so work st...
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more.
Gentle AI is a configuration layer for the AI coding agent you already run, built around the observation that agents write code and then forget everything. It does not replace Claude Code, Cursor, Codex or any of the seventeen agents it supports; it sets them up as a deterministic engineering environment with persisten...
Engineering decisions engine that know when they're stale.
Haft is a decision engineering layer for AI coding agents. It addresses a common failure in AI assisted development: a model produces a plausible answer, the team accepts it, and months later nobody can say why the choice was made or whether it still holds. Haft adds structured reasoning skills to your coding agent and...
AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools
HolyClaude is a self hosted AI coding workstation packaged as a Docker image. It bundles CloudCLI, a web interface for coding agents, with a set of command line coding agents and a preinstalled browser, so a repeatable development environment starts with a single docker compose command. Files and credentials stay on th...
Structured skill framework for Claude Code.
MemStack is a skill framework and memory add on for Claude Code. It addresses the way Claude Code forgets a project between sessions by keeping verified facts about the project and injecting them at the start of each session, alongside a library of skills that load when they are relevant to the task. Every remembered ...
Multi-agent harness that runs Claude Code and Codex together as one system
OpenRig coordinates coding agents as a persistent team. A user talks to one lead agent, which delegates to specialist agents, tracks their work and brings answers back, so that Claude Code, Codex and Pi can work together on projects that run for weeks or months. A team is defined in a rig spec that names each agent, i...