Search papers, labs, and topics across Lattice.
CodeNib introduces a multi-view data system that enhances coding agents' ability to serve repository context by creating reusable lexical, dense, and structural views for each repository commit. This system significantly reduces the lifecycle costs associated with context retrieval, achieving median performance improvements of 8.7x and 25.4x in graph and vector updates, respectively. Additionally, it demonstrates a 4.7x reduction in latency for live requests compared to static navigation, while maintaining localization with 50-87% fewer trajectory tokens across five models.
Coding agents can now access repository context 8.7x faster, dramatically improving efficiency in navigating evolving codebases.
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.
Stanford HAI