# GoogleCloudPlatform/scion

> Scion is an open-source orchestration platform for teams of AI agents and the humans working with them; it assigns specialized roles, manages delegation, shared context, and progress visibility across local or cloud environments.

- Magnitude: 3.0 out of 10 — Breakout
- Stars: 1,960 total · +10 stars measured 2026-10-18, 00:22–11:47 UTC, ≈ 20 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: Apache-2.0 · Created: 2026-03-10 · Last push: 2026-10-18
- GitHub: https://github.com/GoogleCloudPlatform/scion · Page: https://gitnova.dev/en/r/GoogleCloudPlatform/scion

## Useful for

- Run Claude Code, Codex, or OpenCode agents as independent processes with per-agent configuration.
- Coordinate multiple agents on a coding task via shared workspaces or separate Git worktrees.
- Set up a hosted Hub for shared access and remote execution across a team.

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 00:22–11:47: 1950 → 1960 stars (+10). This is the change over that interval.
- Estimated end-of-day forecast: about +20 stars, using observed gains and the previous day.
- Elevated gains were measured on the last 3 completed UTC days in a row. Continued growth is not guaranteed.
- Recent forks include notable developers: @phuhao00 (228 followers).

## Star trust

Star growth looks organic.

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

## Numbers

- Forks: 291
- Issues and pull requests: 3,809
- Watchers: 14
- Average over the last week: 34 per day
- Usual pace: 1 per day
- Stars in the last hour (measured): 2
- Latest release: nightly-20261018 (2026-10-18)

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

2026-09-19 … 2026-10-18: 1, 7, 9, 3, 2, 2, 1, 1, 1, 3, 1, 0, 0, 1, 0, 1, 1, 2, 0, 1, 2, 3, 1, 1, 31, 89, 53, 27, 19, 10

## Magnitude by day, last 3 days

10-16 4.1, 10-17 3.8, 10-18 3.0

## More in this category

1. **google-research/harness2** — 8.9 · Breakout · AI agents · Python · +1,349 stars measured 2026-10-18, 02:46–11:45 UTC, ≈ 2,364 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
2. **anthropics/claude-plugins-official** — 8.0 · Breakout · AI agents · Python · +525 stars measured 2026-10-18, 00:21–11:45 UTC, ≈ 1,084 by evening
   Official Anthropic-managed directory of Claude Code plugins: internal plugins plus third-party ones from partners, installable via the built-in marketplace.
   Full card: https://gitnova.dev/en/r/anthropics/claude-plugins-official.md
3. **MadsLorentzen/ai-job-search** — 7.7 · Breakout · AI agents · Python · +981 stars measured 2026-10-18, 00:21–11:45 UTC, ≈ 2,006 by evening
   A job application framework built on Claude Code: evaluates postings, tailors CVs, and writes cover letters. Runs locally, focused on the Danish job market.
   Full card: https://gitnova.dev/en/r/MadsLorentzen/ai-job-search.md
4. **anomalyco/opencode** — 7.6 · Breakout · AI agents · TypeScript · +614 stars measured 2026-10-18, 00:21–11:45 UTC, ≈ 1,247 by evening
   Open source AI coding agent with terminal and desktop interfaces. Ships with a build agent (full edit and command access) and a read-only plan agent for code analysis.
   Full card: https://gitnova.dev/en/r/anomalyco/opencode.md
5. **android/skills** — 7.1 · Breakout · AI agents · Kotlin · +178 stars measured 2026-10-18, 00:21–11:45 UTC, ≈ 358 by evening
   A repository of AI-optimized modular instructions (SKILL.md) that help agents follow Android development best practices from developer.android.com. Installed via Android CLI or as a plugin for Claude Code and Codex.
   Full card: https://gitnova.dev/en/r/android/skills.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 2026-10-18 11:55 UTC, updated every 30 minutes.