YujunZhou/tellonce

README preview

# Tellonce

**English** · [中文](README.zh.md)

[![arXiv](https://img.shields.io/badge/arXiv-2606.13174-b31b1b.svg)](https://arxiv.org/abs/2606.13174)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

> Stop re-explaining yourself to your AI coding agent. Tellonce
> remembers the corrections you make and — when you ask it to — enforces them, so
> the same mistake doesn't come back. In our evaluations, held-out preference
> violations drop from **100% to 2.0%** on out-of-distribution coding-agent
> tasks ([research below](#-the-research-behind-it)).

You told your agent to stop writing scratch files to `/tmp`. To reply in your
language. To leave unrelated code alone. Three turns later it does it again.
Tellonce can scan turns for preferences, pitfalls, and workflow rules, record
them in a shared local store, and hard-enforce the ones you care about.

It is **non-blocking and privacy-conservative by default**: installation enables
local rule retrieval, but automatic model-backed memory upsert and hard

View full repository on GitHub →