codex Tools

Cindy is an open-source AI agent that integrates multiple AI models and harnesses into a single, ready-to-use system. It solves the problem of fragmented AI tools by providing a unified agent that can switch between models and harnesses mid-task without losing context, enabling real work completion in projects and apps. It's designed for developers and teams who need a powerful, configurable, and continuous AI assistant that is both immediately usable and adaptable over time.

Agents is a multi-harness plugin marketplace for AI coding tools like Claude Code, Cursor, and GitHub Copilot. It solves the problem of fragmented, tool-specific agent ecosystems by providing a central hub for discovering and using skills across different platforms. This project is for developers and teams who use multiple AI coding assistants and want a consistent, extensible set of capabilities available everywhere they work.

Graphify transforms any codebase—including its docs, SQL schemas, configs, and PDFs—into a deterministic, queryable knowledge graph. It solves the problem of fragmented, hard-to-navigate software knowledge by creating a single, persistent map of all code and documentation, enabling engineers to get evidence-backed answers and see the impact of changes instantly. It's built for developers and teams in regulated or complex environments who need auditable understanding and want to run the parsing engine fully on-device, without uploading code or relying on vector stores.

cmux is a free, open-source terminal for macOS built on Ghostty's rendering engine. It solves the problem of terminal clutter and context switching by providing vertical tabs with git status, notification rings for AI agents, and an in-app browser. It's designed for developers and engineers who multitask with coding agents, need to manage multiple sessions, and want a programmable, native terminal experience.

pstack-claude provides rigorous, multi-agent workflow implementations of Poteto's pstack methodology, translated for Claude, Codex, Pi, and other major AI coding assistants. It solves the problem of vendor lock-in and inconsistent agent behavior by offering standardized, high-quality workflows across different AI harnesses. This repository is for developers and teams who want reliable, reproducible AI-assisted coding patterns that work seamlessly whether they're using Claude, Gemini, GitHub Copilot, or other AI coding tools.

codebase-memory-mcp is an MCP server that indexes repositories into a persistent knowledge graph of functions, classes, and dependencies. It solves the problem of AI agents inefficiently reading files one-by-one, enabling structural queries with ~120x fewer tokens. It's for developers and teams using AI coding assistants like Claude Code who need fast, local, and deep codebase understanding.

Oh My Hermes is a comprehensive plugin suite that adds intelligent routing, long-term memory, and optimized workflows to the Hermes Agent coding assistant. It solves the problem of managing multiple AI models and executors by providing a unified, configurable layer that orchestrates tasks to the right tool based on your setup and preferences. It's for developers and teams who use Hermes Agent professionally and want to maximize its efficiency with model pooling, skill packages, and executor-neutral contracts.

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows

This repository is a curated collection of extracted system prompts from leading AI models like Anthropic's Claude, OpenAI's ChatGPT, Google's Gemini, and others. It addresses the problem of opaque AI behavior by revealing the foundational instructions that guide these systems, providing transparency for researchers, developers, and enthusiasts. The collection is regularly updated, serving as a valuable resource for anyone interested in understanding, comparing, or reverse-engineering how these AI models are fundamentally directed to operate.

OmniRoute is an open-source AI gateway that provides a single OpenAI-compatible endpoint to access over 350 providers and 1200+ models, including many free options. It solves the problem of vendor lock-in and high costs by automatically routing requests to the cheapest or most available provider with quota-aware fallback. It's built for developers using AI coding assistants like Cursor, Copilot, and Claude Code who want maximum flexibility, reliability, and token savings.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

This is a library of 50 open-source marketing skills for AI agents like Claude Code, Codex, and Cursor. It solves the problem of democratizing advanced marketing expertise—like CRO, SEO, and analytics—by encoding it into skills AI agents can use. It's built for technical marketers, growth engineers, and founders who want to leverage AI for scalable marketing execution.

Build a custom Codex Desktop theme from any image with a free browser-local builder. Preview five workspace views, check readability, and export data-only files with no sign-up or image upload.

Humanizer is an agent skill that transforms AI-generated writing by removing robotic patterns and unnatural phrasing. It solves the problem of content that feels artificial, helping writers, marketers, and developers produce text that resonates with human readers. This tool is ideal for anyone using AI assistants who needs polished, natural-sounding output for blogs, emails, or communications.

Atlas is a native macOS editor built to manage the work around coding—research, planning, and knowledge—alongside the AI agent threads that turn them into commits. It solves the problem of fragmented workflows by providing a unified planning surface where teams of humans and multiple AI agents can collaborate efficiently. It's for developers and engineering teams who use AI coding assistants like Claude, Codex, and Gemini and want to coordinate their work in a single, local-first application.

Router is a model router for agentic systems that intelligently directs each prompt to the most cost-effective model capable of handling the task, typically in under 50ms. It solves the problem of overspending on expensive frontier models for simple coding prompts, allowing engineering teams to maintain quality while dramatically reducing token spend. It's designed for developers and organizations using AI coding assistants like Claude Code, Codex, and Cursor who want to optimize their AI infrastructure costs without changing their workflow.

Archify is an agent skill that transforms plain English descriptions of systems into beautiful, interactive HTML diagrams. It solves the problem of creating and maintaining accurate, up-to-date architecture, workflow, and sequence diagrams by generating them directly from conversation. It's for developers, architects, and teams who need to quickly visualize, share, and verify system designs with motion, exploration, and crisp export built-in.

Hermes Agent is a persistent, multi-platform AI assistant that grows with you. It solves the problem of fragmented AI tools by providing a single agent with unified memory that works across Telegram, Discord, Slack, CLI, and more. It's for developers, teams, and power users who need an automated assistant that remembers context, schedules tasks, delegates work, and securely browses the web—all from one intelligent core.

Sub2API is an open-source relay service that consolidates access to multiple AI subscriptions like Claude, OpenAI, Gemini, and Grok into a single interface. It solves the problem of managing and paying for multiple expensive AI services individually by enabling cost-sharing through pooled subscriptions. This tool is designed for developers, teams, and cost-conscious users who want efficient, unified access to various AI models while leveraging native tool functionality and reducing per-user expenses.

Ruflo is an agent meta-harness for building and orchestrating intelligent multi-agent systems. It solves the complexity of coordinating autonomous AI workflows by providing adaptive memory, RAG integration, and self-learning intelligence. It's designed for developers and teams building advanced conversational AI, autonomous swarms, and complex, coordinated AI applications.

Obsidian Skills is a set of tools that enables AI agents to read from and write to Obsidian vaults using its command-line interface and open formats like Markdown and JSON Canvas. It solves the problem of AI assistants being unable to directly access or manipulate personal knowledge bases, bridging the gap between conversational AI and structured note-taking. It's designed for developers, researchers, and power users who want their AI agents to seamlessly integrate with and act upon their Obsidian-based knowledge systems.