Back
developer-toolsdata-search

blink

Multiple Jev walkers navigate a repository tree one directory choice at a time.

What Jev decides

Which visible file or subdirectory should a walker inspect next.

Each walker sees only the current directory entries and uses Choice to select the most promising file or subdirectory for a natural-language query, producing traceable routes through the codebase.

CHOICE
Jev role
Route independent search walkers through the most promising repository paths.
Input
The natural-language query, current path, immediate child names, and walker history.
Output
A Choice distribution over the current directory entries.
Decision frequency
At every directory step for every active walker.
Fallback
Return ranked paths and traces for human inspection rather than asserting a final answer.
Author reported · Source reviewed

How it works

Input
The natural-language query, current path, immediate child names, and walker history.
Jev
CHOICE
Output
A Choice distribution over the current directory entries.

Overview

blink treats code search as navigation rather than global retrieval. Starting at the repository root, independent walkers repeatedly ask Jev which immediate child is most likely to contain the answer. The output preserves each path and probability distribution, making the search route inspectable.

The prototype does not build embeddings or a vector index. Its search quality depends on names and local directory context, and the repository does not declare a license, so reuse terms should be confirmed with the authors.

Language
TypeScript
License
Not declared
Author
Ellipsis
Sources checked Sep 21, 2026

Sources

Related projects