# stablyai/orca

> Orca is an ADE for running a fleet of parallel coding agents (Claude Code, Codex, OpenCode, etc.) in isolated git worktrees with a unified interface, mobile companion, and remote runtime.

- Magnitude: 4.4 out of 10 — Steady
- Stars: 109,292 total · +276 stars measured 2026-10-29, 00:04–04:59 UTC, ≈ 1,113 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-03-17 · Last push: 2026-10-29
- GitHub: https://github.com/stablyai/orca · Homepage: https://orca.dev · Page: https://gitnova.dev/en/r/stablyai/orca

## Useful for

- Fan one prompt across five agents at once and compare results in separate worktrees
- Monitor agent completion and send follow-ups from your phone via the mobile app
- Run agents on a remote box over SSH with full file editing and terminals

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:04–04:59: 109016 → 109292 stars (+276). This is the change over that interval.
- Estimated end-of-day forecast: about +1,113 stars, using observed gains and the previous day.
- About 128 forks a day — people are taking the code.

## Star trust

Star growth looks organic.
- Hardly anyone watches for updates: 146 watchers for 109,292 stars.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 6,902
- Issues and pull requests: 35,428
- Watchers: 146
- Average over the last week: 1,067 per day
- Usual pace: 1,089 per day
- Stars in the last hour (measured): 48
- Latest release: v1.4.244 (2026-10-29)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 722, 813, 665, 563, 661, 865, 646, 693, 797, 670, 579, 740, 893, 931, 924, 1044, 919, 1045, 1459, 1552, 1529, 1638, 1376, 1070, 1009, 1084, 1176, 1009, 1010, 276

## Magnitude by day, last 14 days

10-16 5.2, 10-17 5.2, 10-18 5.1, 10-19 5.8, 10-20 6.3, 10-21 5.2, 10-22 5.5, 10-23 5.0, 10-24 4.6, 10-25 4.4, 10-26 4.8, 10-27 4.8, 10-28 4.5, 10-29 4.4

## Similar by description

1. **pingdotgg/t3code** — 4.5 · Steady · AI agents · TypeScript · +51 stars measured 2026-10-29, 00:03–04:59 UTC, ≈ 283 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
2. **ParadevAI/Paradev** — 2.9 · Steady · AI agents · TypeScript · +10 stars measured 2026-10-29, 00:06–05:01 UTC, ≈ 46 by evening
   Paradev is an agentic IDE desktop app for macOS that runs 100+ CLI coding agents (Claude Code, Codex, Cursor Agent, etc.) in parallel, each in its own Git worktree, with a built-in diff viewer, terminals, browser previews, automations,…
   Full card: https://gitnova.dev/en/r/ParadevAI/Paradev.md
3. **kdlbs/kandev** — 1.1 · Steady · AI agents · Go · +0 stars measured 2026-10-29, 00:11–05:07 UTC, ≈ 3 by evening
   Self-hostable Kanban and development environment that orchestrates multiple coding-agent CLIs in parallel with an integrated editor, terminal, and code review workspace.
   Full card: https://gitnova.dev/en/r/kdlbs/kandev.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 05:11 UTC, updated every 30 minutes.