Brennan Benson
5cc502cc55
* fix(mobile): keep terminal input composable while the connection is cut Fixes #6713. While the socket was down every input control on the mobile session screen was hard-disabled by the single canSend gate — the keyboard would not even open, and everything typed during the outage was silently discarded. Split the gate: canCompose (local composing, survives an outage) vs canSend (needs the live socket). The buffered command box stays editable offline and holds the text; the send button, accessory keys, and live-input capture stay connection-gated; the live/buffered mode toggle stays tappable so live-mode users can reach the compose box. The return-key submit path holds composed text instead of firing a doomed RPC. Also reset the live-input mirror when the connection drops: bytes sent into a stalled link are lost but were recorded as delivered, so the first post-reconnect send replayed stale fragments or emitted phantom erases (observed as `YZZYecho CLEANLINE` corrupting the next command on device). * fix(mobile): stop stalled terminal input replaying into the PTY after reconnect Device verification of the first commit surfaced the real replay vector for the second defect: sendRequest parks in waitForConnected while disconnected, so live-mirror deltas queued behind a dying send drain into the connect wait and fire on the next socket — bytes typed during an outage executed tens of seconds later (observed on device as the prompt reading `nOPQ` after reconnect with no post-recovery typing). Add SendRequestOptions.failWhenDisconnected — reject now instead of parking — and opt in every keystroke-grade terminal send: live mirror, accessory keys, buffered command send, and gesture arrows. Deliberate command sends (initialPrompt on terminal create) keep the connect wait. terminal.send param construction moves to terminal-send-request.ts and the accessory raw-send tail to terminal-live-accessory-raw-send.ts. Re-verified on simulator through a blackhole cut-proxy: text typed during the stall no longer replays, and the first post-recovery command executes verbatim. * test(mobile): assert route-slice anchors are unique so pins cannot slice the wrong region * docs(mobile): trim replay-fix comments to one-line rationale
Orca
中文 · 日本語 · 한국어 · Español · Français · Português
The AI Orchestrator for 100x builders.
Run Codex, ClaudeCode, OpenCode or Pi side-by-side — each in its own worktree, tracked in one place.
Download Orca
Features
Mobile CompanionMonitor and steer your agents from your phone — get notified when an agent finishes and send follow-ups from anywhere. |
 |
Parallel WorktreesFan one prompt across five agents, each in its own isolated git worktree — compare the results and merge the winner. |
 |
Terminal SplitsGhostty-class terminals with WebGL rendering, infinite splits, and scrollback that survives restarts. |
 |
Design ModeClick any UI element in a real Chromium window to send its HTML, CSS, and a cropped screenshot straight into your agent's prompt. |
 |
GitHub & Linear, NativeBrowse PRs, issues, and project boards in-app — open a worktree from any task and review without a context switch. |
 |
SSH WorktreesRun agents on a beefy remote box with full file editing, git, and terminals — auto-reconnect and port forwarding included. |
 |
Annotate AI DiffsDrop comments on any diff line and ship them back to the agent — review, edit, and commit without leaving Orca. |
 |
Drag Files to AgentsVS Code's editor with autosave everywhere — drag files or images straight into an agent prompt. |
 |
Orca CLIAgents drive Orca too — script every workflow with |
 |
Also in the box:
- Quick open — Search across worktrees, files, agents, commands, and repo context without leaving your flow.
- Account switcher & usage tracking — See Claude and Codex usage and rate-limit resets, and hot-swap accounts without re-logging in.
- Rich repo previews — Preview Markdown, images, PDFs, and repo docs in the workspace.
- Computer Use — Let agents operate desktop apps and visible UI when a workflow needs real interaction.
- Notifications and unread state — Know when an agent finishes or needs attention, then mark threads unread to come back later.
- And many, many more — we ship daily, so this list is perpetually behind. The changelog is the real feature list.
Supported Agents
Works with any CLI agent — if it runs in a terminal, it runs in Orca.
Claude Code
Codex
Grok
Cursor
GitHub Copilot
OpenCode
MiMo Code
Amp
OpenClaude
Antigravity
Pi
oh-my-pi
Hermes Agent
Devin
Goose
Auggie
Autohand Code
Charm
Cline
Codebuff
Command Code
Continue
Droid
Kilocode
Kimi
Kiro
Mistral Vibe
Qwen Code
Rovo Dev
+ any CLI agent
Install
Desktop — macOS, Windows, Linux
- Download from onOrca.dev
- Or grab a build directly: macOS Apple Silicon · macOS Intel · Windows (.exe) · Linux AppImage · All builds
- Running
orca serveon a headless Linux server? See the headless Linux server guide.
Or via a package manager:
# macOS (Homebrew)
brew install --cask stablyai/orca/orca
# Arch Linux (AUR) — or stably-orca-git to build from source
yay -S stably-orca-bin
Mobile Companion — iOS, Android
Pair with your desktop app to monitor and steer your agents from your phone.
- iOS: Download on the App Store or join TestFlight
- Android: Download APK 0.0.36
Community & Support
-
Discord: Join the community on Discord.
-
Twitter / X: Follow @orca_build for updates and announcements.
-
WeChat: If group 5 is full, you can join group 6.
-
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.
Signed Builds
Windows code signing sponored/provided by SignPath.io, certificate by SignPath Foundation.
License
Orca is free and open source under the MIT License.