Show HN: Antfly: Distributed, Multimodal Search and Memory and Graphs in Go

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.

Key Features

• Hybrid search: full-text (BM25), dense vectors, and sparse vectors (SPLADE), all in one query
• RAG agents: built-in retrieval-augmented generation with streaming, multi-turn chat, tool calling, and confidence scoring
• Graph indexes: automatic relationship extraction and graph traversal queries
• Multimodal: index and search images, audio, and video with CLIP, CLAP, and vision-language models
• Distributed: Raft consensus, automatic sharding and replication, horizontal scaling
• SIMD / SME acceleration: vector operations use hardware intrinsics via go-highway on x86 and ARM

Ecosystem

Antfly provides a comprehensive suite of tools including Antfarm (web dashboard), pgaf (PostgreSQL extension), and dedicated SDKs for Go, TypeScript, and Python. The Termite submodule handles ML inference tasks like embeddings and OCR automatically.

Architecture and Reliability

The system uses a multi-raft design with separate consensus groups for metadata and storage. Reliability is verified through end-to-end chaos tests and formal specifications using TLA+ for critical distributed protocols like transactions and shard splitting.

Licensing

The core server is licensed under Elastic License 2.0 (ELv2), while SDKs, React components, and other tools are under Apache 2.0.