The structure scan added to the daemon's receive path cost 4x more than the
JSON.parse it guards: it indexed the string per character, allocating a
one-character string for every byte, and walked string bodies one byte at a
time even though a string's contents carry no structure.
Read char codes instead, and skip each string body to its closing quote in
one indexOf. Two cursors keep that skip linear: a monotonic escape cursor so
backslash lookups never rescan, and a hoisted closing-quote index that is
re-derived only when the escape cursor passes it. Deriving the closing quote
inside the escape loop instead would rescan the tail once per escape, which
is quadratic on a payload carrying escaped text -- 2.3s on a 4 MB body.
Same input, same verdict: 505,720 differential cases against the previous
char-by-char implementation -- 240,000 randomized over a structural / escape /
unicode alphabet under four limit sets, plus every string up to length 5 over
{ } [ ] , : " \ a -- produce identical results, including the thrown
resource and limit. Dropping the closing-quote refresh reintroduces
mismatches, so the coverage is not vacuous.
20k scans of a 2 KiB message: 286ms -> 5.3ms. The guard now costs less than
the parse it protects, which takes the daemon's fragmented-feed overhead from
2.95x down to 1.44x. On a 4 MB escape-dense body: 14.0ms -> 0.9ms.
Co-authored-by: Orca <help@stably.ai>
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
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 0.0.32
Community & Support
-
Discord: Join the community on Discord.
-
Twitter / X: Follow @orca_build for updates and announcements.
-
WeChat: All other groups are full, now we're on group 5.
-
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.










