Install Antfly, load data, and run your first queries

One call that answers a customer's question from your help articles, with reranking and pruning so it stays quiet when it has no evidence

A React page with live results and facets, plus an answer box that streams a grounded answer with sources, all on one Antfly table

An n8n AI Agent that answers from your Antfly table over hosted MCP, with no application code between the two

New tickets stream out of PostgreSQL and get assigned a team by the resolved tickets that look most like them

A repo index that answers both exact symbol lookups and intent questions, returned as a context block sized to your model's budget

An Antfly table that mirrors a PostgreSQL table on its own, every insert, update, and delete included, with PostgreSQL still the system of record

One request that plans a question, researches each part in parallel, and returns a report whose every citation points at a document you own

One query that matches exact words and meaning at once, with fusion, reranking, and pruning tuned for the results you actually want

A push-to-talk dictation endpoint that returns clean written text, and a streaming session that returns transcript segments while the user is still speaking

A table whose audio recordings are transcribed at write time, chunked with the moment in the recording each chunk came from, and searchable next to your other documents

Choose branches or follow a graph path through a retrieval-step navigation policy.

Run LightOnOCR-3-0.8B and 4B document parsers through Antfly's native inference runtime

Use macOS native OCR, file transcription, and Apple Intelligence text generation in Antfly

Plan media once and produce independent embeddings, transcripts, and supervised predictions.

How one query composes full-text, vector, filters, graph traversal, exact sort, and cursor pagination over a table's physical indexes

How one full-text, vector, or graph index unions the records that enrichments generate, and how to tell when it is ready

The model runtime inside Antfly, what it runs, and how to pull and configure models for it

How Antfly decides whether a local model artifact can load, which artifacts are verified, and which are refused

Model revisions, artifact formats, dependencies, and reproducible local installs

How the embedded single-file profile of Antfly works, what it shares with a normal instance, and how data moves between the two

Index and search images, audio, and documents with executable Antfly workflows