Show HN: Antfly: Go에서 구현한 분산 멀티모달 검색 및 메모리와 그래프
Source: Hacker News
Overview
Hey HN, I’m excited to share Antfly: a distributed document database and search engine written in Go that combines full‑text, vector, and graph search. Use it for distributed multimodal search and memory, or for local development and small deployments.
I built this to give developers a single‑binary deployment with native ML inference (via a built‑in service called Termite), meaning you don’t need external API calls for vector search unless you want to use them.
Capabilities
- Multimodal indexing: images, audio, video
- MongoDB‑style in‑place updates
- Streaming RAG (retrieval‑augmented generation)
Distributed Systems
- Multi‑Raft setup built on etcd’s library
- Storage backed by Pebble (CockroachDB’s storage engine)
- Metadata and data shards each have their own Raft groups
Single Binary
antfly swarm provides a single‑process deployment with everything running. Ideal for local development and small deployments. Scale out by adding nodes when you need to.
Ecosystem
- Ships with a Kubernetes operator
- Includes an MCP server for LLM tool use
Native ML Inference
Antfly ships with Termite, a built‑in service similar to Ollama for non‑generative models as well (embeddings, reranking, chunking, text generation).
- No external API calls needed
- Supports external providers if desired: OpenAI, Ollama, Bedrock, Gemini, etc.
License
Antfly is released under Elastic License v2 (not OSI‑approved). You can use, modify, self‑host, and build products on top of it, but you cannot offer Antfly itself as a managed service. This trade‑off aims to balance sustainability with source availability.
Contact
Happy to answer questions about the architecture, the Raft implementation, or anything else. Feedback welcome!
Comments
https://news.ycombinator.com/item?id=47414291 (Points: 39, Comments: 17)