Jinwoo-HandOrca 202fd9c5a3 fix(terminal): write PTY output live and de-overlap reattach restores
Eliminates the duplicated-TUI-output and broken-wide-char glyph artifacts
that appeared when switching to a worktree after leaving it for a while.

Two structural fixes:

1. Single-source restore on reattach. handleReattachResult now enforces
   strict precedence (snapshot > replay > coldRestore) and paints exactly
   one source per reattach. Painting both daemon snapshot and relay replay
   doubled the same lines because their tails overlap. Snapshot/replay
   still ack any superseded coldRestore so the daemon does not redeliver.

2. Always-live xterm writes. PTY output now flows straight into xterm
   regardless of pane visibility. The visibility-gated buffer
   (pendingWritesRef + chunked drain + fit-epoch dedup) was the source
   of the cursor-on-strange-line and broken-glyph bugs: bytes accumulated
   while hidden then flushed into xterm at stale cols on resume, before
   fitAllPanes() could correct the dimensions. The visibility prop now
   only controls WebGL suspend/resume (GPU resource management).

Also adds an inline comment at openTerminal() pinning Unicode 11
activation before any caller-driven write — wide-char widths bake into
the buffer at the active unicode version, so writing into a v6-default
xterm corrupts CJK/emoji/ZWJ layouts.

New regression tests:
- snapshot wins over replay when both present
- replay wins over coldRestore (and still acks)
- Unicode-11 ordering: open → loadAddon:unicode11 → activeVersion=11 → write
- live writes regardless of visibility prop

Co-authored-by: Orca <help@stably.ai>
2026-05-07 01:24:07 -04:00
2026-04-06 23:32:45 -07:00
2026-05-04 20:42:03 -07:00
2026-03-16 22:27:51 -07:00
2026-03-28 10:19:14 -07:00
2026-05-07 05:03:46 +00:00

Orca Orca

Supported Platforms Discord Follow on X

English · 中文 · 日本語 · Español

The AI Orchestrator for 100x builders.
Run Claude Code, Codex, or OpenCode side-by-side across repos — each in its own worktree, tracked in one place.
Available for macOS, Windows, and Linux.

Download 🐋

Orca Screenshot

Supported Agents

Orca supports any CLI agent (not just this list).

Claude Code   Codex   Gemini   Pi   Hermes Agent   OpenCode   Goose   Amp   Auggie   Autohand Code   Charm   Cline   Codebuff   Continue   Cursor   Droid   GitHub Copilot   Kilocode   Kimi   Kiro   Mistral Vibe   Qwen Code   Rovo Dev


Features

  • No login required — Bring your own Claude Code or Codex subscription.
  • Worktree-native — Every feature gets its own worktree. No stashing, no branch juggling. Spin up and switch instantly.
  • Multi-agent terminals — Run multiple AI agents side-by-side in tabs and panes. See which ones are active at a glance.
  • Built-in source control — Review AI-generated diffs, make quick edits, and commit without leaving Orca.
  • GitHub integration — PRs, issues, and Actions checks linked to each worktree automatically.
  • SSH support — Connect to remote machines and run agents on them directly from Orca.
  • Notifications — Know when an agent finishes or needs attention. Mark threads unread to come back later.

Install

Mac, Linux, Windows

Alternatively, install from a package manager:

macOS (Homebrew)

brew install --cask stablyai/orca/orca

Arch Linux (AUR)

# Precompiled binary
yay -S stably-orca-bin

# Build from GitHub source
yay -S stably-orca-git

[New] Annotate AI Diff

Comment directly on AI-generated diffs.

Annotate any line in an AI-generated diff with your feedback, then send it back to the agent to revise. Keep the review loop tight — no copying line numbers, no context switching.

Orca Annotate AI Diff — comment on AI-generated diffs and send feedback to the agent


[New] Hot Swap Codex Accounts

Multiple Codex accounts? Switch in one click.

If you run multiple Codex accounts to get the best token deal, Orca lets you hot-swap between them instantly — no re-login, no config files. Just pick an account and keep building.

Orca Codex Account Switcher — hot swap between multiple Codex accounts


[New] Per Worktree Browser & Design Mode

See your app. Click any element. Drop it into the chat.

Orca ships with a built-in browser right inside your worktree. Preview your app as you build, then switch to Design Mode — click any UI element and it lands directly in your AI chat as context. No screenshots, no copy-pasting selectors. Just point at what you want to change and tell the agent what to do.

Orca Design Mode — click any UI element and drop it into the chat


[New] Introducing the Orca CLI

Agent orchestration from your terminal.

Let your AI agent control your IDE. Use AI to add projects to your IDE, spin up worktrees, and update the current worktree's comment with meaningful progress checkpoints directly from the terminal. Ships with the Orca IDE (install under Settings).

npx skills add https://github.com/stablyai/orca --skill orca-cli

Community & Support

  • Discord: Join the community on Discord.
  • Twitter / X: Follow @orca_build for updates and announcements.
  • Feedback & Ideas: We ship fast. Missing something? Request a new feature.
  • Privacy: See the privacy & telemetry docs for what anonymous usage data Orca collects and how to opt out.
  • Show Support: Star this repo to follow along with our daily ships.

Developing

Want to contribute or run locally? See our CONTRIBUTING.md guide.

S
Description
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
Readme MIT
1.9 GiB
Languages
TypeScript 95.1%
JavaScript 4.1%
Swift 0.2%
HCL 0.2%
CSS 0.1%