#278 · Primary category: AI Coding Assistants

SeaGOAT

ai ai-project code-search code-search-engine embeddings grep grep-like hacktoberfest hacktoberfest2023 llm regular-expression ripgrep vector-database vector-embeddings

local-first semantic code search engine

Project last updated:08/28/26

GitHub Stars

1.3K

Forks

91

Contributors

26

License

MIT

Why we included this project

SeaGOAT is a code search tool for people who want to ask their codebase questions, not just match patterns. You start a local server per repository, it builds vector embeddings of the code, and plain-language queries like "where are the numbers rounded" work alongside classic regular expressions when you need exact control. Everything runs on your machine, so teams with private or proprietary code don't have to send source to a cloud API. Output handling is a nice touch: results render through bat when color is on, drop to grep-style formatting in pipelines, and the server's HTTP API lets you build custom retrieval features on top. It also factors in Git history when ranking results, so finding your way around an unfamiliar repository becomes a targeted search rather than a hunt.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category