antfly: AI DB in Go

Building a Distributed Search Engine in Pure Go — Antfly Blog

Antfly is a distributed document database and search engine written entirely in Go. It combines full-text search (BM25), vector similarity, sparse vectors (SPLADE), and graph traversal in a single binary. It also ships with built-in ML inference for embeddings, reranking, and chunking — so you can go from raw documents to production RAG without reaching for external APIs.

Run antfly swarm and you get a fully functional node with search, ML inference, a dashboard, and an MCP server — all in one process. Need to scale? Add more nodes and Antfly handles shard splitting and replication automatically.


antflydb/antfly @GitHub

Antfly is a distributed search engine built on etcd's raft library. It combines full-text search (BM25), vector similarity, and graph traversal over multimodal data — text, images, audio, and video. Embeddings, chunking, and graph edges are generated automatically as you write data. Built-in RAG agents tie it all together with retrieval-augmented generation.

Go 1.26 introduced the experimental simd/archsimd package, giving Go programs native access to SIMD instructions. Antfly uses go-highway — a portable SIMD library inspired by Google's Highway — to write vector operations once and run them on AVX2, AVX-512, ARM NEON, or a pure Go fallback.