antflydb/antfly

Antfly is a search-and-inference database written in Zig. One engine carries full-text (BM25), dense, and sparse vector indexes plus graph traversal over the same table, and the models that chunk, embed, rerank, transcribe, OCR, and extract run inside the process. Embeddings, chunks, entities, and graph edges are generated automatically as you write data, and built-in RAG agents tie it together. The same engine runs as a single .aflite file, a single node with a hot standby, a multi-Raft cluster, or serverless over object storage.
Quick Start
These quickstarts run without authentication and are intended for local development. Keep Docker ports bound to loopback. Before allowing remote access, enable authentication and provision a unique admin password, then configure TLS at a reverse proxy.
That gives you the Antfarm dashboard at http://localhost:8080 — playgrounds for search, RAG, knowledge graphs, embeddings, reranking, and more.
See the quickstart guide for a full walkthrough.
Lite, inference, or a database server
| Product | How it runs | License |
|---------|-------------|---------|
| Antfly Lite | An embedded .aflite database through libantfly, Zig, Go, Python, Rust, TypeScript, or browser WASM; local file commands through antfly-lite lite | Apache 2.0 |
| Antfly inference | In-process inference, browser WASM (wasm32/wasm64), or the independent antfly-inference executable and inference APIs | Apache 2.0 |
| Antfly database server | antfly standalone, distributed clusters, or serverless deployment; database HTTP APIs and the dashboard | ELv2 |
The Apache antfly-embedded release archive bundles antfly-lite,
antfly-inference, libantfly, its C header, and the private inference worker,
with runtime files and license notices. Python/npm embedded packages use the same
library without installing public commands. Go/Rust consumers
link the library from the archive or a local build using its relocatable
lib/pkgconfig/libantfly.pc metadata.
Zig applications can fetch the independent Apache
antfly-embedded-source_ .tar.gz release package. It exports the
embedded and inference modules and native/WASM artifacts without a server
checkout; see the Zig package guide.
Build the Apache Lite CLI and native library from source:
The Lite build installs its CLI, libantfly, and the C header. To serve that file over HTTP, use the full database server executable:
The standalone server uses the same Apache engine under ELv2. See LICENSING.md for the source boundaries and third-party licenses.
Features
- **Hybrid search** — full-text (BM25), dense vectors (RaBitQ-compressed with SPFresh-style updates), and sparse vectors (SPLADE), fused with reciprocal rank or relative score fusion in one query
- **Full-text search** — Lucene-style segments with highlighting, geo, regex, wildcard, and fuzzy queries, plus English and ten Snowball stemmer languages
- **RAG agents** — built-in retrieval-augmented generation with streaming, multi-turn chat, tool calling (graph traversal, plus web search through an Exa connection), confidence scoring, and TOON document rendering to cut prompt tokens
- **Query-builder agent** — turns a natural-language question into a structured Antfly query, with evaluation metrics to measure retrieval quality
- **Graph indexes** — automatic relationship extraction and graph traversal over your data
- **Multimodal** — index and search images, audio, and video with CLIP, CLAP, and vision-language models
- **Reranking** — cross-encoder and late-interaction (ColBERT, ColQwen2) reranking with score-based pruning to cut the noise
- **Aggregations** — stats, terms facets, histogram, date histogram, range, and geo-distance aggregations for analytics
- **Transactions** — ACID transactions at the shard level with distributed coordination