$ mayajaal init --watch-all-agents

One terminal.
Every AI coding agent you run.

Mayajaal is the control plane for developers running multiple AI coding agents at once. Track Claude Code and GitHub Copilot sessions across every repo — live status, diffs, and approvals, in a single pane of glass. Offline-first, so the terminal never waits on the network.

▶ launch dashboardview docs →
no credit card · brew install mayajaal · works with your existing CLI agents
mayajaal — session monitor — zsh
agenttaskstatusupdated
claude coderefactor auth middleware → jwt rotationRUNNING2s ago
copilotgenerate unit tests for payments/webhook.tsREVIEW41s ago
codexmigrate api routes to edge runtimeMERGED4m ago
cursorfix flaky e2e test: checkout.spec.tsRUNNINGjust now
claude codewrite changelog for v2.3.0 releaseMERGED12m ago

plugs into the agents you already use

◆ Claude Code◆ GitHub Copilot CLI◆ Codex CLIsoon◆ Cursorsoon◆ Aidersoon
// features

Built for devs drowning in agent tabs

Stop tab-switching between five terminals. Mayajaal gives every session a home, a status, and an audit trail.

Unified session feed

Every Claude Code and Copilot session streamed into one live, scrollable terminal feed — filterable by repo, agent, or status.

Real-time status

See exactly what's running, waiting on approval, blocked, or merged — no more guessing which agent is stuck in a loop.

Offline by default

The local database is the source of truth and the terminal dashboard never touches the network. Sync is a queue that drains when you reconnect — a flight or an outage costs you a delay, not your history.

Diff-aware review

Inspect file diffs from any agent before they touch main. Approve, reject, or hand back to the agent with one keystroke.

Multi-repo, multi-branch

Track sessions across every repo and branch your agents are working in, with the git remote and branch captured per session.

Alerts & webhooks

Get pinged in Slack or terminal-bell when an agent needs input, hits an error, or finishes a long-running task.

Full audit log

Every prompt, diff, and approval logged and searchable — know exactly what an agent changed, and why.

// how it works

Three commands to full visibility

Mayajaal wraps your existing agent CLIs — no migration, no new workflow.

1

Install the daemon

A lightweight background process that watches agent CLI activity on your machine or CI runner.

curl -sL mayajaal.dev/install | sh
2

Connect your agents

Point Mayajaal at your Claude, Copilot, Codex and Cursor sessions — auto-detected in most setups.

mayajaal connect --agent claude,codex
3

Open the dashboard

Watch every session live in your terminal or browser. Approve, kill, or re-prompt from one place.

mayajaal dashboard --watch
# one-liner install
curl -sL https://mayajaal.dev/install | sh
// pricing

Start free. Scale with your agents.

Every plan includes unlimited agent connections on your local machine.

Solo

For individual developers running agents locally.

$0/forever
  • Up to 2 agents connected
  • Live session dashboard
  • 7-day session history
  • Community support
get started

Pro

For devs and small teams running agent fleets.

$19/mo
  • Unlimited agents & repos
  • Diff-aware review queue
  • Slack / webhook alerts
  • Unlimited session history
  • Priority support
start free trial

Team

For orgs standardizing on AI-assisted dev.

custom
  • Everything in Pro
  • SSO & role-based access
  • Org-wide audit logs
  • Self-hosted option
  • Dedicated support
contact us
// faq

Common questions

Which coding agents does Mayajaal support?

Claude Code and GitHub Copilot CLI are what we're building against today — both verified against the CLIs' actual behaviour, not just their docs. Codex CLI, Cursor and Aider are next, through the same plugin interface.

What actually leaves my machine?

By default, your sessions sync to your account so the web dashboard matches your terminal — that includes prompts and assistant responses. It is opt-out, not opt-in: run in local-only mode and nothing leaves at all, or drop a .mayajaalignore in any repo to sync metadata only for that project. Everything works fully offline either way, because the local database is the source of truth and the cloud is a copy of it.

What about secrets in my transcripts?

Agent sessions pick up API keys, tokens and .env contents as a matter of course, so Mayajaal strips them before anything is written to disk — not just before it syncs. Files like .env, .pem and credentials are redacted wholesale rather than scanned. Redactions are marked in the UI so you can see one happened. Run `mayajaal redact --test` to see exactly what the rules catch on your own sessions before you trust them.

Does it work offline?

Completely. The daemon writes to a local database and the terminal dashboard reads only from that — it never touches the network. Sync is a queue that drains when you reconnect, so a flight, a VPN, or an outage on our side costs you nothing but a delay.

Is there a CLI-only mode, no browser required?

Yes. mayajaal dashboard --watch runs a full-screen live TUI in your terminal. The web dashboard is optional, and so is signing in at all.

What platforms are supported?

macOS and Linux, as a single native binary with no runtime dependencies. Windows is planned but not yet tested.

Stop guessing what your agents are doing.

Install Mayajaal and get a live view of every AI coding session in under two minutes.

▶ install mayajaalread the docs →