Kanevry/session-orchestrator

34 stars · Last commit 2026-06-21

Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi. MIT community plugin.

README preview

# Session Orchestrator

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
[![Version](https://img.shields.io/badge/version-3.9.0-blue.svg)](CHANGELOG.md)
[![Tests](https://img.shields.io/badge/tests-10%2C000%2B-brightgreen.svg)](docs/telemetry/telemetry-claims.md)

Turn ad-hoc agent sessions into a repeatable loop with verification gates — **loop engineering** for software work. You design the loop (`research → plan → execute in waves → close`); Session Orchestrator runs it on top of your existing agent, with the guards, telemetry, and cross-session memory that keep a long agent run honest. Inter-wave reviews catch regressions before they ship; carryover issues mean nothing slips through.

Works with **Claude Code, Codex CLI, Cursor IDE, and Pi** — same skills, commands, and hooks across all four. Community plugin (MIT, **not affiliated with Anthropic**) for solo devs and small teams.

## A session in three commands

```text
/session feature    # research + Q&A — inspect git, issues, history, then agree on scope
/go                 # execute in 5 typed waves, with a quality gate between each
/close              # verify every item, commit cleanly, file carryover issues for the rest
```

That is the whole loop. `/plan` and `/evolve` extend it (see [Lifecycle](#lifecycle-at-a-glance)), but you can start with just these three.

View full repository on GitHub →