better-agent-terminal

Better Agent Terminal

A Tauri-powered terminal aggregator with multi-workspace support and built-in AI agent integration

Manage multiple project terminals in one window, with built-in Claude Code and Codex agent panels, file browser, git viewer, snippet manager, and remote access — all in a single Tauri app.

Version 3.0 is the Tauri-only release. The Electron runtime has been removed; the app now uses a Rust/Tauri host, a React renderer, and a small bundled Node sidecar only where JavaScript SDK/runtime support is still required.

Download Latest Release

Mobile Apps

Mobile apps require Better Agent Terminal v3.1.3 or later.

Screenshots

Claude Code Agent Panel — Built-in AI agent with permission controls, status line, and streaming output

Terminal — Run persistent terminals alongside your agent for long-running commands and monitoring

File Browser — Browse and preview project files without leaving the app

Git Viewer — View commit history and diffs at a glance

Features

Workspace Management

• Multi-Workspace — Organize terminals by project folders; each workspace binds to a directory
• Drag & Drop — Reorder workspaces freely in the sidebar
• Groups — Categorize workspaces into named groups with a filter dropdown
• Profiles — Save and switch between multiple workspace configurations (local or remote)
• Detachable Windows — Pop out individual workspaces to separate windows; auto-reattach on restart
• Per-Workspace Env Vars — Configure custom environment variables per workspace
• Activity Indicators — Visual dots showing which workspaces have active terminal processes
• Double-click to rename, right-click context menu for all workspace actions

Terminal

• Split-panel layout — 70% main panel + 30% scrollable thumbnail bar showing all terminals
• Multiple terminals per workspace — Powered by xterm.js with full Unicode/CJK support
• Agent presets — Pre-configured terminal roles: Claude Code, Claude Code (worktree), Codex Agent, or plain terminal
• Git worktree isolation — Spawn Claude agents in an isolated worktree to prevent destructive changes to your main working tree
• Tab navigation — Switch between Terminal, Files, and Git views per workspace
• File browser — Search, navigate, and preview files with syntax highlighting (highlight.js)
• Git integration — Commit log, diff viewer, branch display, untracked file list, GitHub link detection
• GitHub panel — Browse PRs and issues directly from the Git tab
• Snippet manager — Save, organize, search, and paste code snippets (SQLite-backed with categories and favorites)
• Markdown preview — Preview .md files in a dedicated right sidebar panel with live file watching and right-click context menu
• Worker panel (Procfile) — Run multiple processes from a Procfile in a single tab with combined log view and per-process start/stop/restart controls, inspired by Overmind
• Per-terminal prompt history — Access previous commands per terminal session

Claude Code Agent

• Built-in Claude Code via SDK — Runs the agent directly inside the app; no separate terminal needed
• Message streaming with extended thinking blocks (collapsible)
• Permission modes — Multiple levels of tool execution control:
  • Default — Approve each tool call individually
  • Accept Edits — Auto-approve file edits, prompt for other tools
  • Plan mode — Agent proposes a plan file first; approve the plan to auto-execute
  • Bypass — Full auto-approval (use with caution)
• Subagent tracking — See spawned subagent tasks with progress indicators, elapsed time, and stall detection
• Session resume — Persist conversations and resume them across app restarts
• Session fork — Branch off from any point in a conversation with pending prompt auto-send
• Rest/Wake sessions — Pause and resume agent sessions from the context menu to save resources
• Effort level — Configure default effort level (high/medium/low) for new agent sessions
• Auto-compact — Automatically compact context when token count exceeds a configurable threshold

Statusline

A configurable status bar at the bottom of the agent panel, with 15 items across three zones (left / center / right):

Items can be reordered, colored, and toggled on/off via a drag-and-drop template editor in Settings.

Cache Cost Awareness

• Cache history — Per-turn cache read/write breakdown with cost calculations per model (Opus, Sonnet, Haiku)
• Cache TTL countdown — Optional floating badge in the top-right corner showing remaining time for 5-minute and 1-hour cache TTLs; updates every 30 seconds, only appears after 1 minute of idle
• Cache expiry warning — Pre-send confirmation dialog when >150k cached tokens have expired (>1 hour), preventing accidental full-price reprocessing

Account & Usage

• Multi-account switching — /switch to manage and switch between multiple Claude accounts
• Usage monitoring — Track API rate limits (5-hour and 7-day windows) via Anthropic OAuth or Chrome session key
• Context usage panel — Visualize token usage breakdown by category (code, conversation, tools, memory, MCP, etc.)

UI & Interaction

• Image attachment — Drag-drop or use the attach button (up to 5 images per message)
• Clickable URLs — Markdown links and bare URLs open in the default browser
• Clickable file paths — Click any file path in agent output to preview it with syntax highlighting and search (Ctrl+F)
• Ctrl+P file picker — Fuzzy-search project files and attach them to the conversation context
• Skills & Agents panels — Browse available slash commands and agent configurations in the right sidebar
• Markdown preview search — In-pane Ctrl+F search inside markdown previews and file previews
• Long MCP tool output collapse — Auto-collapse oversized MCP tool results with a one-click expand
• Notifications — Dock badge, sound, and system notifications on agent completion (configurable)
• Update notifications — Automatic check for new releases on GitHub

Codex Agent

Optional alternate agent backend powered by the Codex app-server, managed by the Rust host using the bundled @openai/codex runtime. Pick Codex Agent (or Codex Agent (worktree)) from the agent preset list when creating a terminal.

• GPT-5.5 / 5.4 / 5.3-codex / o4-mini / o3 / GPT-4.1 — Switch models inline; ChatGPT login or OpenAI API key
• Sandbox modes — read-only, workspace-write, or danger-full-access
• Approval policies — untrusted, on-request, or never (auto)
• Worktree preset — Spawn Codex in an isolated git worktree, same as the Claude worktree flow
• Session resume — JSONL transcripts under ~/.codex/sessions/ are auto-indexed; resume hits a local cache so re-opening a thread is fast even with months of history
• Inline plan approval — Codex plan items render as approvable blocks in the panel

Semantic Code Navigation (cx)

Optional integration with cx — a tree-sitter-based CLI that gives agents file overviews, symbol search, definitions, and references without spinning up a language server. Useful for cutting context tokens on large codebases: agents can run cx overview (~20 tokens) before deciding which files to actually read.

When enabled in Settings → Agents → cx semantic navigation, BAT:

• Detects cx on PATH (or uses a custom binary path)
• Appends a short system-prompt section telling the agent to prefer cx overview / symbols / definition / references over full file reads
• Sets CX_CACHE_DIR to a per-app cache directory so repeated queries are fast

Install:

After installing, run cx lang add <language> for each language you want grammars for (e.g. rust, typescript, python), then toggle the option in BAT settings. The toggle is off by default — agents continue to work normally without cx installed.

Internationalization (i18n)

• English, Traditional Chinese (繁體中文), Simplified Chinese (简体中文)

Keyboard Shortcuts

Slash Commands