Open Source Shell Projects
A shell is a program that lets people interact with an operating system by entering commands, running scripts, and combining tools. Shells make routine tasks repeatable, provide access to system functions, and support workflows that can be faster or more precise than using graphical interfaces. They are used on personal computers, servers, and other devices, and can be adapted for different levels of experience and control.
Open source shell tools include command interpreters, configuration frameworks, plugins, and utilities for managing scripts and terminal workflows. When choosing one, consider compatibility with your operating system and existing scripts, learning curve, license, documentation, maintenance activity, and integration with other tools. Shells and related tools are useful to developers, system administrators, and anyone who wants to automate tasks or customize their command-line environment.
40 repositories · updated October 4, 2026
aport-agent-guardrails: Authorize AI Agent Actions Before Execution
APort adds policy checks before supported AI agent tools run, helping teams limit prompt-injection risks and unauthorized actions. It provides runtime integrations and GitHub repository checks, with local or hosted verification options.
aidevops: Coordinate AI Agents Across Development and Operations
An OpenCode plugin and shell-based framework for coordinating AI agents across software delivery, DevOps, and business workflows. It combines specialist guidance with isolated Git work, verification, and automation for teams seeking a more durable alternative to one-off AI chats.
agent-plugins: Install Curated AI Coding Assistant Bundles
agent-plugins packages curated skills, MCP servers, and specialist agents into category-based plugins for VS Code, GitHub Copilot CLI, and Claude Code. It suits developers who want reusable assistant capabilities without assembling each integration themselves.
actions: Run Outfitter Agents in GitHub Actions
Run an Outfitter profile as a headless agent job in GitHub Actions. Use it to automate reviews or repository tasks on schedules and events, with configurable harnesses, permissions, browser access, and session transcripts.
antivibe: Learn and Audit Code with Claude Code
AntiVibe is a Claude Code skill that turns files or codebases into learning guides or architectural audits. Use it when you want to understand design choices and trade-offs, rather than rely on a generated code summary.
autoresearch: Run Goal-Driven Improvement Loops with Coding Agents
Autoresearch turns Claude Code, OpenCode, or OpenAI Codex into an agent that makes focused changes, verifies them against a metric, and keeps or reverts each attempt. It suits developers who can define a goal and a mechanical way to measure progress.
product-manager-skills: Add PM Workflows to AI Coding Tools
A reusable Markdown skill that helps Claude Code, Codex, Cursor, and Windsurf handle product management tasks. Use it for structured discovery, SaaS metrics analysis, PRD reviews, roadmaps, and career coaching.
Product-Manager-Skills: Apply Product Management Frameworks with AI
A library of structured product management skills that guides AI agents and PMs through discovery, strategy, delivery, research, and lifecycle work. Useful when teams want more consistent, explainable PM outputs across supported agent platforms.
agent-skills: Structure AI-Assisted Development from Specs to PRs
A collection of reusable skills for AI coding agents, covering specification writing, implementation, review, testing, and autonomous sprint workflows. Useful for teams that want repeatable processes and clearer quality gates across agent sessions.
awesome-shell: Discover Command-Line Tools and Shell Resources
A community-curated directory of shells, terminal utilities, development tools, customization options, and learning guides. Use it to explore the command-line ecosystem and find tools suited to a particular shell or workflow.
superpowers: Guide Coding Agents Through Software Development
Superpowers adds a structured development methodology to coding agents, from clarifying requirements and planning through test-driven implementation and review. It suits developers who want repeatable workflows across supported agent tools.
DocumentServer: Host Collaborative Online Office Editors
ONLYOFFICE Docs provides self-hosted editors and viewers for documents, spreadsheets, presentations, forms, and PDFs. It suits teams and product integrators that need real-time editing embedded in a collaboration platform or application.