Overview

A fleet of autonomous coding agents, available at code.foxl.ai and inside the Foxl app

Foxl Code

Foxl Code is a fleet of autonomous coding agents. You describe work in natural language; an orchestrator plans it, spawns coding agents on isolated cloud VMs, and drives them all the way to open pull requests - opening GitHub Issues, pushing branches, and pausing for your review when it needs you.

Foxl Code is available in two places:

  • code.foxl.ai - the standalone web interface.
  • Inside the Foxl app (web at app.foxl.ai, desktop on Mac/Windows, and iOS) - accessible via the product switcher in the sidebar. Same account, same credits.

Foxl Code runs on AWS Bedrock AgentCore. Each coding agent gets its own isolated microVM with a real filesystem and full terminal access - it is not a sandboxed snippet runner.

The short version

  1. Chat with the orchestrator about what you want built or fixed.
  2. It writes a Task Document - a plan where each checkbox becomes one pull request.
  3. You confirm once. From there the orchestrator spawns a coding agent per checkbox.
  4. Each agent runs a real coding CLI (Claude Code, Kiro, or Codex) in its own VM, pushes a branch, and opens a PR.
  5. If an agent needs you, it pauses in review; you reply and it resumes from exactly where it stopped.
  • How it works - the orchestrator, Task Documents, and the plan-confirm-fan-out flow.
  • Tasks - the task lifecycle and what each state means.
  • Coding agents - Claude Code, Kiro, and Codex backends, and how to pick one.
  • GitHub - connecting repos, the GitHub App, branches, and PRs.
  • Budgets and tiers - the credit model, per-task budgets, and plan limits.
  • Autonomous loop - let the orchestrator check back and drive tasks on its own.
  • Resume from review - replying to a paused agent and continuing its session.

On this page