A curated directory of product CLIs, developer tools, and terminal apps — verified for humans, scripts, and AI agents.
>_$ bun
An all-in-one JavaScript runtime, package manager, bundler, and test runner.
>_$ gh
GitHub on the command line: repositories, pull requests, issues, Actions, releases, and API calls.
>_$ glab
GitLab’s official CLI for merge requests, issues, pipelines, releases, snippets, and self-managed instances.
>_$ http
A human-friendly HTTP client with JSON, sessions, auth, and formatted output.
>_$ lazygit
A keyboard-driven terminal UI for staging, rebasing, branching, and Git history.
>_$ playwright
Cross-browser end-to-end testing and browser automation from the command line.
>_$ ast-grep
Search, lint, and rewrite code using syntax-aware structural patterns.
>_$ just
A convenient command runner for project-specific development recipes.
>_$ mise
Manage language runtimes, environment variables, and project tasks.
>_$ uv
A fast Python package, project, tool, and environment manager.
>_$ biome
A fast formatter and linter for modern web projects.
>_$ buf
Lint, build, generate, and manage Protocol Buffer APIs.
>_$ circleci
Validate CircleCI configuration, run jobs locally, manage orbs, and inspect pipelines.
>_$ cz
Create consistent conventional commits through an interactive prompt.
>_$ cookiecutter
Create projects from reusable templates using interactive variables.
>_$ deno
A secure JavaScript and TypeScript runtime with built-in developer tooling.
>_$ docker
Build images, run containers, manage networks and volumes, and work with Docker contexts.
>_$ goreleaser
Build and publish Go binaries, archives, packages, and release notes.
>_$ jest
A JavaScript testing framework with snapshots, mocking, and coverage.
>_$ newrelic
Manage New Relic entities, workloads, deployments, profiles, and NerdGraph operations.
>_$ nx
A smart monorepo platform with caching, generators, and affected commands.
>_$ sentry-cli
Create Sentry releases, upload source maps and debug files, and manage deployment metadata.
>_$ shellcheck
Static analysis that finds bugs and portability problems in shell scripts.
>_$ shopify
Build Shopify apps and themes with local development, previews, extensions, and deployment workflows.
>_$ task
A portable task runner that uses readable YAML Taskfiles.
>_$ tig
A text-mode interface for browsing Git history and changes.
>_$ turbo
A high-performance build system for JavaScript and TypeScript monorepos.
>_$ twilio
Manage Twilio resources, phone numbers, messages, serverless functions, and API requests.
>_$ vegeta
A versatile HTTP load-testing tool designed for constant request rates.
>_$ vite
A fast frontend development server and production build tool.
Common questions about CLI tools, Agent CLIs, and command line automation
A CLI, or command-line interface, lets you control software by typing commands in a terminal instead of clicking through a graphical interface. CLI tools are useful for development, automation, scripts, CI pipelines, and repeatable operations.
An Agent CLI is either a command-line tool for operating an AI agent or a conventional CLI designed to be called reliably by AI agents. Agent-friendly CLIs expose clear commands, non-interactive options, predictable output, and meaningful exit codes so an agent can plan, execute, and verify work.
Yes. AI coding agents can invoke many of these CLIs through a shell to work with repositories, cloud services, databases, productivity apps, and deployment systems. Tools marked Agent-ready are especially suitable for scripted or autonomous use, but authentication and permissions still need to be configured safely.
The best CLI tools for AI agents support non-interactive commands, stable flags, structured or parseable output, standard input and output, documented authentication, and reliable exit codes. These features make results easier for an agent to interpret and verify without manual intervention.
Choose an official CLI when you need first-party support, close alignment with a service API, and predictable updates. A community CLI can be a better fit when it offers a simpler workflow or capabilities the official tool lacks. Review its repository, maintenance activity, permissions, and installation instructions before use.
Use an OS keychain, environment variables, or a dedicated secret store instead of placing API keys in repositories, prompts, or shell history. Give people and AI agents least-privilege access, start in read-only or test environments, and confirm that automated commands support previews, explicit confirmation controls, and reliable exit codes.
