·
A practical guide to the tools bringing AI into your terminal.
AI CLI tools are changing how developers write code. Instead of switching to a browser or IDE extension, you stay in your terminal and work with an AI that can read your codebase, edit files, and run commands. Here is a practical overview of the major options.
All four tools below can be installed from Yaw's built-in install wizard, which handles dependencies automatically.
Claude Code is Anthropic's AI coding assistant. It runs in your terminal, reads your project files, and can create, edit, and delete files with your approval. It is an agentic tool - you give it a task and it works through it step by step.
macOS / Linux: curl -fsSL https://claude.ai/install.sh | bash
Windows: irm https://claude.ai/install.ps1 | iex
Multi-file changes, refactoring, building new features, and understanding unfamiliar codebases. Claude Code excels at tasks that require reading many files and making coordinated changes. Its CLAUDE.md context system lets you encode project conventions once and have them applied consistently across sessions.
If you launch Claude Code from Yaw Terminal, Claude Code Yaw Mode layers a curated bundle of CLAUDE.md rules, 23 slash commands, and dispatch sub-agents on top of every session - useful when you want a project-spanning baseline without copy-pasting CLAUDE.md across repos.
Codex is OpenAI's CLI agent. Like Claude Code, it operates directly in your terminal and can read, write, and execute within your project. It is built in Rust and uses OS-level sandboxing to isolate command execution.
npm install -g @openai/codex
Security-conscious workflows where you want OS-enforced boundaries on what the AI can access. The sandbox modes are the most granular of any AI CLI tool - you can give Codex full autonomy within your workspace while blocking network access and protecting .git. The AGENTS.md standard also means your project context works across multiple AI tools, not just Codex.
Gemini CLI is Google's open-source (Apache 2.0) AI coding agent. As of June 18, 2026, the free individual tier ended - Google now routes consumer users to the closed-source Antigravity CLI, and running gemini-cli itself requires a paid API key (Vertex AI or AI Studio). The Apache-2.0 repository stays public, and enterprise users on Gemini Code Assist keep full support. We covered the change and the alternatives in Gemini CLI Is No Longer Free.
npm install -g @google/gemini-cli
Developers already invested in the Gemini models who are willing to bring a paid API key. The open-source CLI is unchanged and still capable - the extension ecosystem, GEMINI.md context, and Google Search grounding make it strong for tasks that need current information or specialized tools - but the free-of-charge path for individuals is gone.
Vibe CLI is Mistral's command-line coding assistant. It takes a different approach from the task-oriented agents above - instead of working through multi-step plans autonomously, it focuses on rapid, conversational iteration. You describe what you want, it generates code, and you refine together in tight loops.
macOS / Linux: curl -LsSf https://mistral.ai/vibe/install.sh | bash
Windows: pip install mistral-vibe
Quick prototyping, creative exploration, and developers who want a back-and-forth conversation with the AI rather than handing off a task. The clarification system makes it more cautious than fully autonomous agents - good for situations where you want the AI to check before making changes. Also the only tool here that runs entirely on European infrastructure (Mistral is based in Paris).
Regardless of which tool you use, your terminal setup matters:
The most important setup. Run the AI tool in one pane and keep a regular shell in the other. You can check files, run tests, and verify changes while the AI works. Most terminals support this - split vertically so the AI gets the wider pane.
AI CLI tools produce a lot of output. Make sure your terminal has enough scrollback to review what the AI generated. At least a few thousand lines.
Each tool reads its own context file: Claude Code uses CLAUDE.md (falls back to AGENTS.md), Codex uses AGENTS.md (with configurable fallbacks), Gemini CLI uses GEMINI.md (can be configured to also read AGENTS.md), and Vibe CLI reads AGENTS.md. These files let you encode project conventions, tech stack details, and coding standards so the AI follows them consistently. AGENTS.md is an open standard under the Linux Foundation, adopted by 60,000+ projects - if you maintain one, it works across most tools out of the box.
Most terminals treat AI CLI tools as ordinary processes - they run, but the terminal doesn't know what they are. Yaw handles this automatically - it recognizes when you start any of these tools and splits a companion shell in the same working directory. It also has a built-in file editor for reviewing AI-generated changes, inline image rendering for viewing screenshots and diagrams alongside your sessions, and context-menu actions (Explain This, Fix This) that send errors directly to an AI provider for help.
If you're new to AI CLI tools, start with whichever matches the AI provider you already use. If you have an Anthropic API key, start with Claude Code. OpenAI key, start with Codex. Gemini CLI now needs a paid Google API key (its free individual tier ended in June 2026), while Vibe CLI is still free with Mistral's Experiment tier. If you're not sure, Claude Code and Codex are the most mature and widely used.
You can use more than one - they all install independently and work in any terminal. Try running a real task (not a toy example) to see how each one handles your actual codebase.
| Tool | Provider | File Editing | Command Execution | Context Files | MCP | Open Source | Free Tier |
|---|---|---|---|---|---|---|---|
| Claude Code | Anthropic | Yes | Yes | CLAUDE.md, AGENTS.md | Yes | No | No |
| Codex | OpenAI | Yes | Yes (sandboxed) | AGENTS.md | Yes | Yes | No |
| Gemini CLI | Yes | Yes | GEMINI.md | Yes | Yes | No (ended Jun 2026) | |
| Vibe CLI | Mistral | Yes | Yes | AGENTS.md | Yes | Yes | Yes |
All four tools support MCP, which means they can connect to external tools and services through a standard protocol. If you use MCP servers across more than one of these clients, Yaw MCP is a local-first orchestrator CLI that wires the same server set into each client from one JSON file you control.
Published by Yaw Labs.