> ## Documentation Index > Fetch the complete documentation index at: https://docs.traycer.ai/llms.txt > Use this file to discover all available pages before exploring further. # Traycer > Plan, preserve, and inspect AI coding work across Tasks, modes, artifacts, chats, terminal agents, files, and git diff. Traycer is a workspace for working with coding agents without losing intent, context, or visibility. You organize work into **Tasks**. Inside a Task, you can use chats, terminal agents, files, git diff, and durable **artifacts** like specs, tickets, stories, and reviews. Each chat or terminal agent runs in **Regular Mode** or **Epic Mode** depending on how much structure the work needs. Download the desktop app, then continue to the Quickstart. ## The Traycer Mental Model A Task is the top-level container for related chats, panels, terminal agents, and artifacts. Select a workspace folder, create your first Task, and run your first coding-agent chat. Use chat sessions, composer controls, permissions, child chats, and terminal agents. Understand the sidebar panels for chats, artifacts, terminals, files, git diff, sharing, and comments. Regular Mode is direct coding-agent work. Epic Mode adds Traycer's structured planning layer. Specs, tickets, stories, and reviews preserve decisions, work items, and review context. Find, filter, reopen, rename, and clean up previous Tasks. Choose whether agent work runs in a workspace folder, a new worktree, or an existing worktree. Set up Codex, Claude Code, OpenCode, Cursor, and Traycer. ## Find What You Need Learn the vocabulary: Tasks, History, Worktrees, panels, modes, and artifacts. Understand chat controls, permissions, child chats, and terminal-agent handoff. Understand pricing, storage, sync, credits, and teams. Extension docs are preserved separately for current extension users.