JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 35
  • Score
    100M100P100Q96173F
  • License UNLICENSED

Multi-AI command layer in your terminal. One prompt → every AI.

Package Exports

    This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@terminalxapp/cli) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

    Readme

    Terminal X CLI

    Multi-AI command layer in your terminal. One prompt — every AI.

    $ tx "build me a landing page with a hero image and audio narration"
    
    plan (3 tasks):
      flux         → generate hero image: SaaS landing concept
      elevenlabs   → narrate intro: 30s warm welcome
      claude-code  → assemble HTML using image + audio
    
    flux: ✓ image generated (1.2 MB) → hero.png
    elevenlabs: ✓ audio generated (340 KB) → narration.mp3
    claude-code: <!DOCTYPE html><html>(12 KB) → landing.html

    Install

    npm install -g @terminalxapp/cli

    Requires Node 22+.

    First-time setup

    tx login

    Opens your browser to terminalxapp.com to authenticate. Your credits, sessions, and connectors all sync — there's no separate CLI account.

    By default the CLI talks to the hosted executor at https://api.terminalxapp.com. To run against a local executor (dev mode), set TERMINAL_X_API=http://localhost:3003 before tx login.

    Usage

    tx                      # interactive agent REPL
    tx "<prompt>"           # one-shot agent prompt
    tx chat                 # cloud-only REPL (image / audio / video gen)
    tx login                # save credentials
    tx logout               # remove credentials
    tx whoami               # show signed-in account
    tx balance              # credits remaining + tier
    tx update               # upgrade to the latest version
    tx --help               # all commands
    tx --version            # version
    tx --debug <cmd>        # verbose output (API URLs, WS state)

    What the agent can do

    The tx REPL is a true coding agent — it can read/write files in your project, run shell commands, search code, hit Git, and chain that with 30+ connectors (Gmail, GitHub, Notion, Stripe, etc.) and 6+ AI models in parallel. Recent highlights:

    • Full-screen terminal UI (v0.7) — the REPL takes over the terminal: transcript streams above a pinned input box with a live status line, native scrollback preserved. esc interrupts the agent mid-turn.
    • Plan mode — the agent drafts a numbered checklist for multi-step tasks and marks steps in real time as it works.
    • Sub-agents — for parallel research and opinion sampling, the agent spawns focused sub-agents that work simultaneously, then synthesizes the results. Try tx "compare Bun vs Node for a high-throughput API".
    • Consult paneltx "should I switch to Postgres or stay with Mongo?" runs the question through Claude, GPT, and Gemini in parallel and returns a synthesized recommendation.

    Differentiation

    • Claude Code = single AI (Anthropic only)
    • Perplexity Computer = web-only, model choice abstracted
    • Terminal X CLI = multi-AI orchestration in your terminal, every AI you have credits for, explicit per-task routing

    Roadmap

    • v0.1–v0.5: streaming, file writes, browser login, project context, auto-update ✓
    • v0.6: plan mode, sub-agents, consult panel, signed-token auth ✓
    • v0.7: full-screen terminal UI + mid-turn interrupt ✓
    • v0.8: OAuth-style loopback login (redirect + code exchange) ← current
    • next: session persistence, multi-line paste, per-prompt credit caps