MEGA Hub
New

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

Published on Jul 27 Submitted by MEGAon Jul 29#1 Paper of the day SysEvol AI Research

Authors

Do you know Zhongming Yu?You can claim authorship or link another user.Do you know Hengjia Yu?You can claim authorship or link another user.Do you know Boqin Yuan?You can claim authorship or link another user.Do you know Shuting Zhao?You can claim authorship or link another user.Do you know Yizhao Chen?You can claim authorship or link another user.Do you know Aryan Dokania?You can claim authorship or link another user.Do you know Mihir Jagtap?You can claim authorship or link another user.Do you know Jiayu Chang?You can claim authorship or link another user.Do you know Yitong Ma?You can claim authorship or link another user.Do you know Yash Jayswal?You can claim authorship or link another user.Do you know Wentao Ni?You can claim authorship or link another user.Do you know Hejia Zhang?You can claim authorship or link another user.Do you know Zhaoling Chen?You can claim authorship or link another user.Do you know Gangda Deng?You can claim authorship or link another user.Do you know Jishen Zhao?You can claim authorship or link another user.

Abstract

Coding agents repeatedly search, navigate, and retain context from evolving repositories, but disconnected indexes, language servers, and task-local histories force repeated discovery and obscure lifecycle costs. CodeNib builds reusable lexical, dense, and structural views per repository commit, maps outputs to repository-relative source ranges, maintains selected views across edits, and serves ranked search, symbol navigation, and bounded context through one runtime. Across 100 snapshots, we map quality-cost frontiers across the repository-context lifecycle. When outputs match an independent rebuild, graph and vector updates are 8.7times and 25.4times faster at the median. On the static-navigation subset matching normalized live-server locations (63% of 1,000 requests), the median per-request live/static latency ratio is 4.7times. Across five models, selected context policies preserve localization with 50--87% fewer trajectory tokens than paired grep/read. Together, these results support multi-view repository-context serving with explicit, operation-specific validity boundaries.

Community

00