<div align="center">

# graphkit

**Run a long coding task as a small graph of agent nodes, not one drifting loop.**

A [Claude Code](https://claude.com/claude-code) skill that turns *"make this production-ready"* into an executor node that does the work and a supervisor node that watches from outside the executor's context and corrects drift before it compounds.

graphkit is **graph engineering** made concrete — the shift from tuning a single agent loop to wiring specialized agent roles into a graph. Two roles today; more planned.

[](LICENSE) [](CONTRIBUTING.md) 

English · [简体中文](README.zh-CN.md)

</div>

---

## The problem

Hand an agent a large, vague goal — *"get this repo to production quality"*, *"push accuracy above baseline"*, *"finish the migration"* — and over dozens of rounds it drifts:

- scope creep: new abstractions, v2 endpoints, config nobody asked for; - fake "done": tests with no production call site, features that compile but do nothing; - a quietly lowered bar: a frozen contract changed, a metric regressed; - a lost thread: no single source of truth, so round 30 contradicts round 5.

The agent cannot catch this in itself: it reasons from the same history that produced the drift, so it will report itself on-spec. You end up reviewing every round by hand.

## From loop engineering to graph engineering

Loop engineering tries to fix this inside the loop — better prompts, more reminders, a bigger context window. It plateaus, because the loop's own history is what corrupts its judgment.

Graph engineering moves the structure outside the model: a small graph of specialized agent roles, each starting from a clean context, connected only by durable, inspectable state. graphkit applies this to one scenario — long-horizon coding — with the s