For your agent
The terminal for your coding agent
Forkbench runs whatever agent you already use. Every tab is a real login shell, so the agent starts exactly as it does in any terminal, and nothing on a task records which agent wrote it. These pages cover the specific friction of running each one, and what changes when it runs here.
Forkbench for Claude Code
claude
Claude Code is Anthropic's coding agent that runs in your terminal, reads your repository, edits files and runs commands.
Read the setupForkbench for Codex CLI
codex
Codex CLI is OpenAI's terminal coding agent, which reads your repository, proposes changes and runs commands from the command line.
Read the setupForkbench for Cursor CLI
agent
Cursor CLI is Cursor's coding agent in the terminal, installed with a one-line script and run as agent. It works interactively or headless with -p for scripts and CI, and it is included with every Cursor plan.
Read the setupForkbench for Gemini CLI
gemini
Gemini CLI is Google's open-source terminal agent, which brings Gemini into the command line to read code, run commands and make changes.
Read the setupForkbench for GitHub Copilot CLI
copilot
GitHub Copilot CLI brings Copilot to the terminal as the copilot command. It answers questions interactively and runs agentic modes where you delegate a task with more autonomy, and it asks for explicit trust before it touches a folder.
Read the setupForkbench for Aider
aider
Aider is an open-source terminal coding agent that pairs with you in your git repository and commits each change it makes.
Read the setupForkbench for OpenCode
opencode
OpenCode is an open-source terminal coding agent that works with a range of model providers rather than being tied to one vendor.
Read the setupRunning something that is not listed? It still works. Any agent you can start from a command line runs in a Forkbench tab, including your own scripts, and claims from the same board as the rest.