Back to directory

Helix

An experimental agent orchestration loop built on the Pi coding agent that takes a work item through implementation specialists and then independently reviews the resulting local pull request through separate PR-control specialists.

Helix

Helix is explicitly not a language model and not a coding agent itself; it is the system that orchestrates coding agents and a deterministic lifecycle policy around them. It takes a work item through a set of implementation specialists and then independently reviews the resulting Git-backed local pull request through separate PR-control specialists, rather than letting the same agent both implement and approve its own change.

It is one project in a related executable reference architecture, alongside a local issue and PR management surface that triggers it, a feature-idea board, an optional decision inbox for delegation policy, and a disposable target application used to exercise and verify the whole loop end to end.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.