Beyond the single terminal: how to manage a fleet of Coding Agents with Orca

Over the past few months, coding agents have moved from experimentation to everyday use in many development teams. Tools such as Claude Code, Codex, Cursor and Copilot CLI have proven reliable across a growing range of tasks: refactoring, writing tests, fixing bugs.

Once the initial phase of adoption and enthusiasm is over, however, a different problem emerges. When agents become more than one and work in parallel on the same repository, the challenge is no longer getting code out of the AI, but governing its production: isolating tasks, keeping the main branch clean and knowing at any given moment which agent is working on which part of the codebase.

This article is the result of a series of tests carried out by several members of Bitrock’s Frontend team, who introduced Orca into their daily workflow to assess its strengths, limitations and room for extension. Below we summarize what emerged: how the tool works, how it differs from the main alternatives, and how the team adapted it to its own needs by developing an internal fork.

Task isolation with Git Worktrees

The key difference between a classic IDE plugin and a tool like Orca lies in the underlying architecture.

If two different agents are asked to work on the same repository in the same folder, they will get in each other’s way and both lose efficiency. Orca solves the problem at its root by leveraging Git Worktrees: every time a task is assigned or a prompt is sent, the system creates an isolated directory tree in the background.

# Typical workflow with the Orca CLI

orca worktree create --branch fix/session-leak --agent claude-code

orca worktree create --branch fix/session-leak-codex --agent codex

# Run the same prompt in parallel on two different models

orca fanout "Find and fix the memory leak in the auth middleware"

The impact on everyday work is immediate:

  1. Zero local conflicts: three agents can work in parallel without any risk of overwriting the files the developer is working on.
  2. Side-by-side comparison: the same task can be sent to different models (e.g. Claude vs Codex), their diffs can be compared, and the user can evaluate the best approach and merge only the valid solution.
  3. Integration with team tasks: an Issue from GitHub or Linear can be opened and its dedicated worktree created with a single click.

Claude Code also uses git worktrees, but only internally, to isolate command execution within its single terminal session. Orca, an open source Agent Development Environment (ADE) designed to coordinate multiple coding agents directly within the developer’s workflow, instead acts as a higher-level orchestrator: it automatically creates and visually manages worktrees so that multiple agents can run in parallel on different branches. This way, Orca makes it possible to compare the diffs produced by each model side by side before merging into the main branch.

Remote monitoring: the companion mobile app

The companion mobile app (available for iOS and Android) extends the experience beyond the terminal: it syncs in real time with local sessions or sessions on remote servers (via SSH), sending push notifications when an agent completes a task or requests confirmation (Human-in-the-loop), making it possible to monitor progress and send feedback remotely.

Orca and the alternatives on the market

Orca enters a market that is booming right now, but with a very specific approach. If we are evaluating how to structure our Developer Experience, the main options fall into three categories:

1. T3 Code vs Orca

T3 Code is another very solid visual orchestrator. The main difference lies in its approach: T3 Code focuses on centralizing chat sessions and multi-provider threads in a single interface, while Orca (and therefore Forca) puts much more emphasis on system-level isolation through Git Worktrees, mobile control and support for agents running on remote machines via SSH.

2. OpenHands

OpenHands takes an end-to-end approach: it provides the agent, planning, the sandbox and the execution environment. Orca follows the opposite logic and positions itself as an external coordination layer. It does not replace the CLIs or subscriptions already in use (Claude Code, Codex and others), but adds a layer of management and orchestration on top of them.

3. Workflow orchestrators (Temporal, LangGraph)

These address a different need: tools like Temporal or LangGraph are used to write and run AI workflows inside applications in production. Orca, on the other hand, helps us developers write code faster during the development phase.

To sum up:

Orca

  • Strength: Fleet management via Git Worktrees, simple and intuitive UI, mobile app
  • Usage model: BYOA (Bring your own CLI agents)
  • Weakness: Learning curve for advanced Git

T3 Code

  • Strength: Single interface for threads and prompts
  • Usage model: Freemium / BYO-Key
  • Weakness: Less focused on remote Worktrees

OpenHands

  • Strength: End-to-end autonomous system
  • Usage model: Open source with sandbox
  • Weakness: Heavier to run locally

Forca: a fork of Orca

Since the project is released under the MIT license, Orca’s real advantage is that you are not bound by the original team’s design choices. If something your workflow needs is missing, you build it.

That is exactly what Davide Ghiotto, Senior Front-end Engineer, did with the help of Elhosain Halili, Front-end Engineer. Using Orca every day for automated programming, they missed a lean, visual way to manage branches and stashes in the style of VS Code.

Instead of adapting or opening a feature request and waiting, you can work on the source code with the help of AI and create your own custom fork: “Forca“. In a short time, they added:

  • A native branch switcher in Source Control, complete with quick commands and sync indicators (pull/push counters).
  • Advanced Stash management, with dedicated submenus for apply, pop and drop, plus an automatic “Stash & Switch” function when a branch switch is blocked.
  • Signed macOS builds, so that anyone on the team can install and use the modified version right away.

This is a great example of how AI is changing the way we approach open source: we no longer simply use tools as they are provided, but shape them around the team’s real needs with minimal effort.

Conclusions

Orca does not make agents smarter: if a model produces wrong solutions or hallucinations, it will keep doing so. Its value lies elsewhere, namely in reducing the cognitive load of context-switching and in making it possible to treat coding agents for what they are today: a group of assistants to whom well-defined tasks can be delegated, to be checked and reviewed with the right tools before changes reach the main codebase.

Our Front-end team’s experience suggests that maturity in adopting coding agents is not measured by the number of agents in use, but by the quality of the process that governs them. Task isolation, structured comparison between alternative solutions and a human checkpoint before merging are practices that go beyond any single tool, and that every team should consider when integrating AI into its development cycle.

Main Author: Daniel Zotti, Team Leader & Tech Leader Frontend @ Bitrock

Do you want to know more about our services? Fill in the form and schedule a meeting with our team!