Multi-agent coding

Several agents. Separate terminals. One place to supervise.

tlbx keeps each Codex, Claude Code, Grok Build, OpenCode or Copilot CLI process in a durable terminal session with its own repository and browser context.

The working model

Every executable worker remains a real terminal session.

tlbx does not replace the coding agents or proxy their model calls. It runs their normal CLIs in native PTYs, preserves the sessions when browsers disconnect and exposes explicit terminal, repository and browser controls to you and to authorized agents.

01

Separate the work

Give concurrent writers separate branches or checkouts. Keep read-only analysis together only when file ownership cannot collide.

02

Launch normal CLIs

Run the provider CLI you already use. Its authentication, model selection and output remain native to that tool.

03

Supervise by state

Use session activity, attention, Git state, terminal output and browser evidence to see what is actually blocked or complete.

04

Reconcile deliberately

Review and integrate the useful work into the primary checkout, then retire temporary workers instead of leaving an invisible fleet behind.

What tlbx adds

Terminal substrate, not another agent framework.

Persistence
Agent turns, test watchers and server processes continue when the supervising browser closes.
Visibility
Session status, attention, terminal history, repository state and the live browser stay attached to the worker.
Control
CLI and API helpers can select sessions, send prompts, inspect output and drive scoped browser validation.
Vendor choice
Codex, Claude Code, OpenCode and ordinary terminal programs use the same session substrate without a provider-specific runtime.

Good fit

Parallel feature lanes, independent review and implementation, long builds, browser-backed validation and work that must survive laptop or browser changes.

Bad fit

Two agents editing the same files without ownership, phantom background workers with no terminal identity, or concurrency added only to make a small task look larger.

Human boundary

tlbx makes work observable and steerable. It does not remove the need to review destructive actions, reconcile branches or decide what should ship.

Common questions

Multi-agent coding FAQ

Does tlbx call Codex or Claude through an API?

No. It runs the normal terminal CLI. Authentication and model usage stay between that CLI and its provider.

Can different agents run at the same time?

Yes. Each runs in an independent PTY. Concurrent writers should use separate branches or checkouts to prevent file collisions.

Can an agent control the browser?

Yes, when explicitly authorized. tlbx exposes scoped browser status, navigation, query, click, text and diagnostic helpers.

Does tlbx replace Git worktrees?

No. tlbx supervises sessions and repositories. Git branches and worktrees remain the isolation mechanism when multiple workers write concurrently.

An unhandled error has occurred. Reload X