Every model, tool and connector an agent can be given.

Long-context reasoning model. The default for agents that plan multi-step work and read large documents end to end.

General-purpose chat model with strong function calling. A good fit for tool-heavy agents and structured extraction.

Multimodal model that reads scanned PDFs, screenshots and diagrams alongside text in the same conversation.

Multilingual embedding model covering Vietnamese and English in one vector space — no separate index per language.

Cross-encoder reranker that reorders retrieved chunks by true relevance before they reach the model's context.

Build an agent as a diagram: steps, branches and loops you can see, run and roll back.

One script tag puts a grounded assistant on your own website, answering from your knowledge base.

Open-weights model you can also run on your own hardware. A cheap default for high-volume, low-stakes answering.

Open-weights model with strong Vietnamese and Chinese. The economical choice for non-English workspaces.

Retrieval-tuned embedding model for English corpora where recall on long technical documents matters.

Speech-to-text for voice notes in chat and for indexing recorded calls and meetings.

Reads an answer back aloud, in chat or as a speech step inside a flow.

Describe, compare or answer questions about an image — attached to a chat turn, or handled by a vision step.

Turns scanned pages and photographed documents into searchable text, keeping the reading order.

Preserves tables as tables during ingestion, instead of flattening them into a row of loose numbers.

Splits documents on structure rather than character count, so a passage retrieved is a passage that makes sense.

Vector similarity and keyword matching run together, then merge — so an exact product code is found as reliably as a paraphrase.

Lets an agent look something up on the public web when the answer is not in your own sources.

Calls an HTTP API you nominate, with the credentials held server-side and never shown to the model.

Fetches a web page and reads it as text — a documentation page, a changelog, a competitor's pricing.

Answers questions from your own database with a read-only query the agent writes and you can read back.

Reads a spreadsheet an agent is given, and writes one back as a downloadable file.

Lets an agent remember what it learned in an earlier run, and search it in a later one.

Attach any Model Context Protocol server and its tools appear to your agents alongside the built-in ones.

Search a connected mailbox and send from it, with the account connected once by its owner.

Search and read documents from a connected Drive, without copying the whole of it into Ragenta.

Reads a sheet as data and appends rows to it — the simplest place to put what an agent produced.

Lists upcoming events so an agent can answer about the week ahead, or prepare for what is on it.

Reads channel history and posts back into a channel — the answer arriving where the question was asked.

Searches issues and opens new ones, so a support conversation can become a tracked bug.

Searches a connected Notion workspace, so internal documentation answers questions without being copied first.

Connect your own database as a read-only data source, over a public address you control.

Runs one question against several versions of an agent at once, so a change can be judged instead of hoped about.