Discover terminal-native tools for AI agents, coding workflows, code review, repo analysis, and deployment.
Query
All tools
Category
All categories
Open Source
All
Anthropic’s terminal coding agent for repo-level work.
Claude Code is Anthropic’s agentic coding system for the terminal. Its official product and docs position it around reading large codebases, editing across files, running tests, and landing work through real developer tools.
OpenAI’s local coding agent that runs directly in your terminal.
Codex CLI is the open-source terminal agent from OpenAI. The official README describes it as a coding agent that runs locally, with ChatGPT sign-in, API-key access, and direct installation through npm, Homebrew, or release binaries.
Google’s open-source terminal agent with search and MCP support.
Gemini CLI is Google’s open-source AI agent for the terminal. Its official README highlights built-in tools for search, shell, file operations, and web fetching, plus MCP support and a documented free tier for personal Google-account sign-in.
The open-source classic for git-first AI pair programming.
Aider remains one of the most established open-source coding CLIs. Its official repo and site focus on making LLM-driven edits directly inside git repositories, which keeps it especially useful for patch-oriented workflows.
Block’s extensible local AI agent for engineering automation.
Goose is an open-source local AI agent from Block that aims beyond code suggestions. Its official README emphasizes autonomous task execution, MCP support, external API interaction, and multi-model configuration in both desktop and CLI forms.
The default bridge from coding agents to pull requests and issues.
GitHub CLI is GitHub’s official command-line tool. It remains foundational for agentic engineering because most coding agents still need a reliable terminal path for pull requests, issue triage, release work, and repository automation.
The fastest low-level search primitive in most agent stacks.
ripgrep stays essential because agentic systems still need fast, gitignore-aware text search. It is not an AI tool, but it is one of the highest-leverage building blocks under modern repo-aware agent workflows.
Astral’s fast Python package and project manager for repeatable agent environments.
uv is Astral’s high-performance Python package and project manager. It matters in agent workflows because reproducible environments, dependency sync, and fast bootstrap times are often the difference between a useful automation loop and a broken one.
The operational CLI every infra-aware agent eventually needs.
kubectl remains the canonical CLI for Kubernetes operations. In AI-assisted engineering, it is the tool that turns a coding agent into something useful for deployment verification, incident response, and live cluster inspection.
