Orkas Orkas
Download GitHub
More use cases: Deep research Chat with documents Content writing Make images Make videos UI design Product development SEO & GEO Office documents Build apps
Home Use cases For Researchers
For Researchers

An AI agent team that
reads your sources.
Uma equipe de agentes de IA que
lê suas fontes.
一支读懂你
参考资料的 AI agent 团队。
あなたの資料を
読み込む AI エージェントチーム。

Ingest papers and PDFs into a local knowledge base, then run literature reviews with citations grounded in your sources. Use Orkas-managed official models or connect your own provider.Adicione artigos e PDFs à base local e faça revisões com citações das suas fontes. Use modelos oficiais gerenciados pelo Orkas ou conecte seu provedor. 把论文和 PDF 导入本地知识库,即可做文献综述并获得基于原始资料的引用。可使用 Orkas 托管的官方模型或连接自有服务商。 論文や PDF をローカルのナレッジベースに取り込み、出典に基づく引用付きレビューを実行できます。Orkas 管理の公式モデルまたは自分のプロバイダーを利用できます。

Runs on your machineReads your local libraryManaged models or your provider
What you can hand off

Research workflows, done as a team

Each spans skills a single assistant would juggle clumsily — Orkas splits them across agents in one conversation.

PDFs → local knowledge base

Drop in papers, reports, and notes; the team chunks and indexes them into a searchable local KB.

  • kb_ingest
  • file_io

Cited, source-grounded answers

Ask in plain language; get answers that quote the exact passage and link back to the file and page.

  • kb_search
  • cite

Literature review & synthesis

Compare findings across papers, surface agreements and gaps, and draft a structured review with a citation table.

  • summarize
  • web_search

Data charts from a prompt

Turn a dataset or table into charts and an interactive explorer — saved to My Apps for reuse.

  • code_exec
  • create_artifact
In one conversation

From a folder of PDFs to a cited answer

You ask the question; the team searches your library and grounds every claim — your sources stay on your machine by default.

Every answer links back to the source
Research team · 2 agents
What do these 18 papers say about scaling laws?
L
Lead agent
Bringing in @researcher to search your Library.
R
Researcher
Searched your Library — 41 passages across 12 files. skill: kb_search
R
Researcher
3 converging findings, 2 disagreements — cited [Kaplan 2020 p.7] · [Hoffmann 2022 p.3].
How it works

Four moves, no config

01

Add your sources

Drop PDFs and notes into a local knowledge base.

02

Ask the question

“Summarize the debate”, “find counter-evidence”, “build a review”.

03

Check the citations

Every claim links back to the exact passage and file.

04

Export the draft

A structured review with a citation table, ready to edit.

Safe with your library

Your sources stay on your machine by default

Local-first

The knowledge base, source files, and notes stay local by default; the selected model service receives the data needed for its calls.

Grounded, not guessed

Answers cite the passage they came from, so you can verify before you cite it yourself.

Managed models or your provider

Official models use Orkas services; own-provider model calls go direct.

See security →
FAQ

Researcher questions

Can an AI agent read my PDFs and answer with citations?Um agente de IA pode ler meus PDFs e responder com citações? AI agent 能读我的 PDF 并给出带引用的答案吗? AI エージェントは私の PDF を読んで引用付きで回答できますか?

Yes. Ingest papers and PDFs into a local knowledge base; a researcher agent answers from those sources and cites the passage and file. Use Orkas-managed official models or connect your own provider.Sim. Adicione artigos e PDFs à base local; o agente responde com passagens e arquivos citados. Use modelos oficiais gerenciados ou seu provedor. 可以。把论文和 PDF 导入本地知识库,研究员 agent 会基于来源回答并引用段落和文件。可使用托管官方模型或连接自有服务商。 はい。論文や PDF をローカルの知識ベースに取り込み、出典箇所とファイルを引用して回答します。公式マネージドモデルまたは自分のプロバイダーを利用できます。

Where are my papers and notes stored?Onde meus papéis e anotações são armazenados? 我的论文和笔记存在哪里? 私の論文やメモはどこに保存されますか?

By default the knowledge base, source files, and chat history stay on your machine. Official models use Orkas services; own-provider model calls go direct. Optional sync stores the data you choose to sync on Orkas servers, and the free edition sends limited usage metadata, not your content.Por padrão, base de conhecimento, arquivos e histórico ficam na sua máquina. Modelos oficiais usam os serviços Orkas; chamadas ao seu provedor vão direto. A sincronização opcional armazena os dados escolhidos no Orkas, e a edição gratuita envia metadados limitados de uso, não seu conteúdo. 默认情况下,知识库、原始文件和对话历史留在本机。官方模型使用 Orkas 服务;自有服务商调用会直连。可选同步会把你选择的数据存到 Orkas,基础版发送有限的使用元数据,不含你的内容。 既定ではナレッジベース、ソースファイル、履歴はマシン上に残ります。公式モデルは Orkas サービス、自分のプロバイダーへの呼び出しは直接送信されます。任意同期は選択したデータを Orkas に保存します。

Which models can the research agents use?Quais modelos os agentes de pesquisa podem utilizar? 研究 agent 可以使用哪些模型? 研究エージェントはどのモデルを使えますか?

Use Orkas-managed official models, or connect OpenAI, Anthropic Claude, Google Gemini, and other providers through OAuth or an API key. Own-provider model calls go direct.Use modelos oficiais gerenciados pelo Orkas ou conecte OpenAI, Anthropic Claude, Google Gemini e outros por OAuth ou chave de API. Chamadas ao seu provedor vão direto. 可使用 Orkas 托管的官方模型,或通过 OAuth/API Key 接入 OpenAI、Anthropic Claude、Google Gemini 等供应商。自有供应商调用会直连。 Orkas 管理の公式モデル、または OAuth/API キーで OpenAI、Anthropic Claude、Google Gemini などを利用できます。自分のプロバイダーへの呼び出しは直接送信されます。

Put a team on your library

Free, open source, runs on your machine.