andyyaro

Orkestra — Development skill for Claude Code

Development community

Local-first orchestration runtime for multiple autonomous coding agents (Claude Code, Codex CLI, Antigravity CLI, and more).

How to install Orkestra

This entry records only its repository, not the path inside it, so there is no exact command to give. Open andyyaro/orkestra and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Orkestra does

Local-first orchestration runtime for multiple autonomous coding agents (Claude Code, Codex CLI, Antigravity CLI, and more). A dynamic director plans, a deterministic kernel enforces.

Alternatives in Development

/autopilot — Autonomous hunt loop with deterministic scope safety and configurable checkpoints 1.2k ★
Claude Code Agent Farm — A powerful orchestration framework that runs multiple Claude Code (cc) sessions in parallel to systematically 704 ★
Evolving Agents — A director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked stat 453 ★

README

Orkestra

[![CI](https://github.com/andyyaro/orkestra/actions/workflows/ci.yml/badge.svg)](https://github.com/andyyaro/orkestra/actions/workflows/ci.yml) [![PyPI](https://img.shields.io/pypi/v/orkestra-runtime.svg)](https://pypi.org/project/orkestra-runtime/) [![Python](https://img.shields.io/pypi/pyversions/orkestra-runtime.svg)](https://pypi.org/project/orkestra-runtime/) [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)

**Coordinate many agents. Deliver one verified result.**

You already use coding agents - Claude Code, OpenAI Codex, Google Antigravity. Orkestra makes **two or more of them work on the same project at once**, safely: every task runs in its own isolated Git worktree, your test commands are the referee, and nothing lands until a *different* agent has reviewed it. Your branches are never touched; finished work waits on a side branch until you accept it.

See it in 60 seconds - free

uv tool install 'orkestra-runtime[tui]'
orkestra demo

No agent CLIs, no logins, no tokens spent - scripted fake agents drive the *real* engine so you can watch the whole lifecycle:

▸ The plan: two independent tasks run in PARALLEL, each in its own
  isolated Git worktree, then a third task builds on both.
  completed verification passed: PASS (exit 0): test -f feature_a.py
  completed review by grace: changes requested (severity medium)
    warning review requested changes (cycle 1)
  completed review by grace: approved (severity none)
  completed task feature-a done (agent ada)
  completed all tasks done
▸ Done: 3 tasks planned, isolated, verified, cross-reviewed, integrated.
  1 review rejection triggered a repair loop (bounded - never spins forever).

That rejection-then-repair is the point: agents check each other, the kernel keeps score, and you only see verified results.