kantord/SeaGOAT
local-first semantic code search engine
Combines vector embeddings with ripgrep for hybrid semantic and regex-based code search, using ChromaDB as a local vector database with no external API dependencies. Operates as a client-server architecture where the persistent server indexes code incrementally without blocking system performance, enabling queries even during indexing. Supports 13+ languages via syntax-aware file filtering and can be self-hosted remotely with optional multi-user access through VPN or network configuration.
1,277 stars.
Stars
1,277
Forks
89
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/kantord/SeaGOAT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
giancarloerra/SocratiCode
Enterprise-grade (40m+ lines) codebase intelligence in a zero-setup, private and local MCP:...
lyonzin/knowledge-rag
Local RAG System for Claude Code - Hybrid search (Semantic + BM25) with MCP integration
blueraai/bluera-knowledge
Local knowledge search for AI coding agents. Index repos, docs, and files with semantic +...
zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
datadrivenconstruction/OpenConstructionEstimate-DDC-CWICR
Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 9...