Submit a resource

Navigation

Back to directory

SeaGOAT

A local, ripgrep-based code search engine that uses vector embeddings to let developers search a codebase by meaning rather than exact text.

Visit website (opens in a new tab)kantord.github.io
SeaGOAT

SeaGOAT is a local search tool that uses vector embeddings so a developer can search a codebase semantically instead of only by literal text, while also supporting regular-expression queries in the same command. It depends on Python 3.11 or newer and ripgrep, and optionally on bat for nicely highlighted results; when used in a pipeline it falls back to a grep-style output format.

Using SeaGOAT starts a small per-repository server, after which queries are run through a short gt or seagoat command from anywhere in the project. Configuration is read from a YAML file, either globally or per project, letting settings such as the server port be adjusted.

SeaGOAT is tested on Linux, with macOS and Windows support described as partial or still needing help, and is released under the MIT license.

More in RAG

See all 540

  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy