Neil
b7d35fa8a8
Mining 16,206 distinct credential-vocabulary lines out of this repo's own tracked files and placing each one row above a real agent composer caret produced **100 refusals across 25 distinct lines**, on Codex, Claude Code and OpenCode. The corpus had `rg` hits and diffs, which carry their own chrome, but no plain formatted source -- and that is the category that leaked. 24 of the 25 are the same shape. `AUTH_QUESTION_ROW_RE` rests on "prose never starts with a bare `?`", which is true and irrelevant: oxfmt puts a ternary's consequent on its own row as `? someValue`, and **5,666 tracked files have one**. `sawAuthQuestion` then returns unconditionally, with no position requirement, so a composer caret directly below could not clear it. Nine of those matched only because `\b(?:log[ -]?in)\b` reads `user.login` as the auth verb. The 25th is the other rule: `CREDENTIAL_ASK_PREFIX_RE` was unanchored, so an ask verb anywhere in a row made a row-final credential noun a prompt -- `// Why: a merely missing or expired bundle must not enter the credential` is a real wrapped comment in this repo, and terminal wrapping makes ending on a noun routine. Three fixes, same discipline as the flow rule already uses: - the ask verb must LEAD its row, modulo decoration and a menu number, so `2. Paste an API key` still reads as a prompt and 60 characters of prose before `enter the` does not; - `.login` is a property access, not an auth verb; - a known composer caret on the bottom row suppresses the question-row rule, because an agent sitting at its own prompt is not asking anyone anything. The caret set deliberately includes a bare `>`. It only suppresses the question-row rule, and the #19749 sign-in dialog -- whose own bottom row is `>` -- matches through `isCredentialPromptLine`, which returns first. Verified: that dialog and the auth-method menu both still refuse. Mined-corpus refusals 100 -> 0, with the mined lines added as a new corpus category so the next widening has to refuse them. Sentinel budget unchanged at 16.2ms/500ms.
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 0.0.48 · Install guide
Community & Support
-
Discord: Join the community on Discord.
-
Twitter / X: Follow @orca_build for updates and announcements.
-
WeChat: Scan to join the Orca community WeChat group 8. Group 8 may be full; if so, scan the Group 9 QR code instead.
-
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.
The relay that pairs the mobile app with a desktop host is also in this repository under
cloud/, with a separate pnpm workspace and setup 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.