Aight aight.cool

Can AI replace Aight?

A focused multi-backend iPhone prototype is a realistic multi-day build when a local companion normalizes each agent protocol, but hardening all four adapters plus Aight's hosted relay, voice, orchestration, sync, and App Store polish is multi-week product work.

Verdict: Half-bot · AI gets you partway; the hard part stays hardBuild time: multi-day prototype; multi-week to harden
Half-bot

01What it costs

$4.99/moPro, monthly
$59.88per year at that price

Checked Aug 11, 2026 · source: aight.cool.

PlanMonthlyBilled yearlyWhat you get
FreeFreeFreeOpenClaw mode: 1 team, 8 agents and 2 group chats; Channels mode: 2 channels and 1 channel group; core chat.
Pro$4.99$2.92/moUnlimited teams, agents, group chats, channels and channel groups.

Hidden costs: Aight supplies only the client/control surface: it does not include AI models, agents or a backend, so model API charges and the self-hosted or cloud agent infrastructure are separate.

02Could AI build it for you?

The core job: Build one SwiftUI client and a local adapter service that can start, resume, stream, interrupt, and approve work across Codex, Claude Code, OpenClaw, and Hermes.

What a working version needs:

  • Mac with Xcode
  • iPhone running iOS 18
  • Node.js 22
  • at least one supported agent installed
  • Apple ID for device signing
  • credentials for each enabled agent
  • Tailscale on both devices

The shared mobile control loop is buildable; maintaining four adapters and the polished remote experience is the hard part.

03What you'd give up

  • managed encrypted relay and push notifications
  • voice mode with local speech models
  • cross-agent teams and group-chat orchestration
  • pre-built agent/team templates and community skill browsing
  • multi-device sync and App Store polish

They pay for one polished client that safely reaches several agent backends from anywhere, keeps sessions in sync, and handles notifications, voice, and approvals without maintaining a custom mobile integration.

04Free and cheaper alternatives

Happyopen-source

A phone remote for Claude Code and Codex, with your computer still doing the work.

Versus paying: Happy is a strong phone remote for Claude Code and Codex, but it lacks Aight’s OpenClaw and Hermes support, multi-agent group chats, voice modes, and built-in health and cost dashboards.

happy.engineering →
Nimbalystopen-source

A visual desk for several coding agents, without turning them into a node graph.

Versus paying: Nimbalyst is a desktop agent workspace and does not provide Aight’s native iOS remote control, voice conversation, or multi-agent group-chat experience.

nimbalyst.com →
Paseoopen-source

One control panel for five coding CLIs; the agents still need a host.

Versus paying: Paseo supports more terminal agents, but its daemon-and-client interface lacks Aight’s polished Apple-native voice, group-chat, gateway-health, and token-cost experience.

paseo.sh →

05The build prompt

Paste this into an AI coding tool (such as Claude, ChatGPT, Lovable or Replit) to build your own version.

prompt.txt
Build me a local-first iPhone client for Codex, Claude Code, OpenClaw,
and Hermes. Requirements:

- Use Swift 6, SwiftUI, and iOS 18. Generate Xcode from a checked-in
  XcodeGen project.yml so `xcodegen && xcodebuild` works on a clean clone.
- Build the Node.js 22 TypeScript companion with Fastify and WebSockets. Expose
  start, resume, prompt, event, approval, interrupt, and capability operations;
  session listing is optional and capability-gated.
- Ship real adapters for all four. Disable unavailable agents at runtime; all
  adapters must compile and pass fixture tests without every agent installed.
- Codex: pin the CLI version, run `codex app-server generate-ts`, and supervise
  app-server over stdio using the generated v2 types.
- Claude Code: use `@anthropic-ai/claude-agent-sdk`, its session APIs,
  async-iterable input for interrupt(), and canUseTool for permissions.
- OpenClaw: use the official Gateway WebSocket client, pair once, request only
  read/write/approvals/questions scopes, and store its device token securely.
- Hermes: use /v1/runs and its event, approval, and stop endpoints; use
  session headers for continuity and discover features from /v1/capabilities.
- Keep backend models in the companion and expose one versioned protocol. The
  iOS app stores its wss:// endpoint and bridge bearer token in Keychain.
- Provide backend/session pickers, streamed Markdown and tool events, approval
  cards, Stop, capability-aware controls, and deny approvals on disconnect.
- Bind to 127.0.0.1 and compare the random `.env` token in constant time;
  expose it only through private Tailscale Serve HTTPS, and never enable Funnel.
- Add bounded reconnects and local completion notifications. No app accounts,
  cloud database, analytics, or telemetry; agent model-provider calls remain.
- Out of scope: hosted relay, voice, cross-backend groups, templates, community
  skills, themes, multi-device sync, and a macOS client.
- Test adapter fixtures plus denial, interruption, and reconnection. README:
  setup for all four, `.env.example`, Tailscale, signing, permissions, limits.

06Open-source starting points

  • Happy: Open-source mobile and web client for Codex and Claude Code with end-to-end encryption.
  • CodexAppMobile: Open-source SwiftUI iOS client for a remote Codex app-server.
Sponsor slot · openFeatured alternative to Aight. A labeled card for one relevant tool.
Book this spot →

App prices, verdicts, alternatives and build prompts are adapted from Can I Vibecode It? (MIT License, © 2026 Rob Hallam). Each price shows the date it was checked and its source. Prices change; confirm on the vendor's site before you decide.