Brennan BensonandOrca
1041ab4f7c
* feat(agent-hooks): introduce relay wire envelope + connectionId stamping Adds the shared `agent-hook-relay.ts` module with the `agent.hook` JSON-RPC notification envelope, the `agent_hook.requestReplay` / `agent_hook.installPlugins` method names, and the `ORCA_FEATURE_REMOTE_AGENT_HOOKS` flag helper. Promotes `AgentHookSource` to `shared/` so the relay can import it without dragging Electron in. Threads a `connectionId: string | null` field through `AgentHookEventPayload`, the `agentStatus:set` IPC contract, and the renderer-bound preload listener. Local hook posts stamp `null`; the relay-forwarded path will stamp from `mux` identity in a later commit. Renderer uses the stamp for stale-event filtering when an SSH connection tears down with notifications still in flight. See docs/design/agent-status-over-ssh.md §1, §5, §8 (commit #1). Co-authored-by: Orca <help@stably.ai> * refactor(agent-hooks): extract shared listener; add relay-side adapter Extracts the listener internals (request parsing, payload normalization, endpoint-file writing, per-CLI extractors, warn-once Sets, slowloris timer helper, request size cap, paneKey caches) from `src/main/agent-hooks/server.ts` into a new transport-agnostic `src/shared/agent-hook-listener.ts`. The shared module uses only Node builtins (no Electron) so it is safe to import from `src/relay/`. Adds `src/relay/agent-hook-server.ts` — a thin HTTP-loopback adapter that wires the shared listener to a `forward(envelope)` callback so `relay.ts` can re-emit each parsed payload as an `agent.hook` JSON-RPC notification on the existing SshChannelMultiplexer. The adapter owns: - 127.0.0.1:0 socket + bearer-token auth, identical shape to the local server - per-paneKey last-payload cache + replayCachedPayloadsForPanes() for the request-driven replay path used after `--connect` reattach (see §5 Path 3) - clearPaneState(paneKey) for PTY-exit eviction (symmetric with local server) - buildPtyEnv() / endpoint-file writing for relay-spawned PTYs Orca's `AgentHookServer` is now a ~200-LoC adapter over the shared listener that owns the IPC fanout, listener replay, and `ingestRemote(envelope, connId)` entry point that bypasses the HTTP path for relay-forwarded events. See docs/design/agent-status-over-ssh.md §3, §8 (commit #2). Co-authored-by: Orca <help@stably.ai> * fix(preload): expose connectionId on agentStatus.onSet type src/preload/index.ts already passes through `connectionId?: string | null` from main, but the PreloadApi declaration in api-types.ts was missing the field. Align the type with the runtime contract so renderer call sites can read connectionId without an `as` cast. Co-authored-by: Orca <help@stably.ai> * fix(agent-hooks): harden ingestRemote + relay replay; review-driven cleanup - ingestRemote: re-run normalizeAgentStatusPayload at trust boundary; trim+validate connectionId/paneKey/tabId/worktreeId - relay: preserve source/env/version through replay via sidecar map; drop sourceFromAgentType fallback that mis-tagged unknown agents - shared listener: exhaustive switch+never on AgentHookSource dispatch chains; extractPromptText returns trimmed values; export MAX_PANE_KEY_LEN - preload: tighten connectionId from optional to required (always sent) - main IPC: reorder spread so explicit envelope fields win on collision Co-authored-by: Orca <help@stably.ai> * chore(docs): drop agent-status-over-ssh design doc from PR The design RFC was useful for authoring this PR series but doesn't belong in-tree — keeping it here would freeze line-number references and design prose against future churn. Folding it into the PR description instead. Co-authored-by: Orca <help@stably.ai> * chore(agent-hooks): widen ingestRemote type for env/version (PR2 prep) Declares `env?: string` and `version?: string` on the `ingestRemote` envelope parameter so PR2 only needs to add the `warnOnHookEnvOrVersionMismatch` callsite, not also widen the type. The fields are forwarded verbatim from the agent CLI POST body on the remote and let Orca's warn-once cross-build / dev-vs-prod diagnostics fire identically on remote-sourced events. Type-only addition; no runtime consumer in this PR. Co-authored-by: Orca <help@stably.ai> --------- Co-authored-by: Orca <help@stably.ai>
Orca
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.
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.
[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.
[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.
[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.