* fix(native-chat): fold thoughts and tool calls between replies into one row A model that thinks before every tool call drew a 'Thought for Ns' row between each call, and each thought also stopped the calls from merging, so a turn read as dozens of alternating rows. The transcript now draws an unbroken stretch of tool calls and thoughts within a turn as one tool run; thoughts read in order inside it when opened and are not counted in its label. * fix(native-chat): keep work runs whole while a turn edits files A live turn that had edited a file kept splitting its newest call or thought off the run (the row carrying the turn's diff rollup could not join), so a lone "Thought for Ns" row came back at the bottom. - Run boundaries are now one pure pass in src/shared (nativeChatWorkRunSpans), applied over the built transcript slots. Section heads end runs by sitting between rows, and rows inside an expanded subagent section are grouped the same way. - The row carrying the turn's diff rollup joins as the run's last member; the run takes the rollup from it and the bar from its head. - A collapsed run reserves one tool row plus a lead's words, not every thought's text. - Lone rows and runs draw through the same MessageRow, with one flat keyed line list, so a row becoming a run no longer remounts (a revealed diff card no longer re-fires its scroll). - A run opens by default while the reader holds one of its thoughts open; the run's own choice still wins. - A drawn thought with no visible text joins a run instead of splitting it. * fix(native-chat): pair each row's result with its own call; keep open thoughts out of runs - A structured journal row's call and result now share one id (the provider's call id, else the row's own id), so a diff or output can no longer pair with an earlier unanswered call in the same work run or folded message. A quiet command followed by edits now shows each diff card under its own call, and the rollup's reveal lands on it. - A thought still being thought, while its turn or subagent works, keeps its own row after the run and joins once it ends. - Removed the rule that opened a run because a thought inside it was open; a thought keeps its own open state inside its run. * fix(native-chat): an open thought the live line lets go of joins its run Only a subagent section keeps a still-running thought out of its run. At the top level the live line owns the open thought; when it lets go (a Stop in flight, a prompt waiting on the reader) the thought now joins the run at once instead of flashing as its own row until the turn ends. * test(native-chat): guard the run row memo; name the slot post-pass test after it Settled work runs must not rebuild their lines and thoughts on every stream frame of the live run. Renames the slot-level run test so it no longer shares a name with the shared span test.
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
Muse
DeepSeek Harness
ZCode
OpenCode
MiMo Code
Amp
OpenClaude
Antigravity
Pi
oh-my-pi
Hermes Agent
Devin
Goose
Auggie
Autohand Code
Charm
Cline
CodeBuddy
Codebuff
Freebuff
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
- Android: Download APK 0.0.52 · 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 11.
-
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.










