kantord/SeaGOAT
local-first semantic code search engine observed · 2026-08-28
Health v2 · maintenance only
72/100
- Activity 93
- Release rhythm 40
- Longevity 83
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: 1
- age_days: 1170
- days_rel: 476
- days_push: 43
- n_releases_24m: 32
Adoption not part of the score
1304 stars · 91 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
SeaGOAT is a local-first semantic code search engine that uses vector embeddings to let developers search their codebase with natural language queries. It runs as a local server with a grep-like CLI, supports regex queries, and integrates with ripgrep and bat for result display.
Use cases
- search my codebase semantically with natural language
- find where numbers are rounded in a large repo
- grep alternative that understands meaning not just text
- locally search code with embeddings without sending code to cloud
- combine regex and semantic queries over a repository
When to choose
- you want semantic code search that runs entirely locally
- you prefer a CLI workflow over IDE plugins
- your codebase is too large to navigate with plain grep
When to avoid
- you need polished Windows support
- you want a hosted or team-shared search service
- you need an IDE-integrated search experience
Facets
cli-tool · maturity active
search-engine vector-database cli llm-inference developer-tools cli python semantic-code-search embeddings grep-alternative local-first code-navigation search command-line linux macos
2 sources
- readme: https://github.com/kantord/SeaGOAT · fetched 2026-08-28 · 2364c91c83af
- homepage: https://kantord.github.io/SeaGOAT/ · fetched 2026-08-29 · 36c6c3c2e4f9
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| kantord/SeaGOAT | main | 72 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem