Paper 2607.25431
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
- Published
- Jul 2026
- Research lab
- Independent
- Citations
- 0
- GitHub
- 74 stars
01 In brief
Summary
CodeNib is a multi-view data system that serves repository context to coding agents by building reusable lexical, dense, and structural views per repository commit, mapping outputs to repository-relative source ranges, and maintaining views across edits.
It addresses three challenges: heterogeneous views (C1), incremental freshness (C2), and agent delivery (C3).
The system compiles views independently, uses Git/LSP-assisted graph repair and content-addressed vector reuse for updates, and serves ranked search, symbol navigation, and bounded context through one runtime.
Evaluations across 100 snapshots show that when outputs match independent rebuilds, graph and vector updates are 8.7x and 25.4x 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 4.7x.
Across five models, selected context policies preserve localization with 50-87% fewer trajectory tokens than paired grep/read.
The system's manifest records artifact status and capabilities, and the runtime loads only required views.
Results support multi-view repository-context serving with explicit, operation-specific validity boundaries.
02 From the paper
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 $8.7\times$ and $25.4\times$ 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 $4.7\times$. 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.