Alternativa de código aberto ao ChatGPT que roda modelos de IA no computador, offline

por Menlo Research

Em portuguêsUsa inteligência artificial
Nota dos leitores
Sem avaliaçõesAvaliar
No ranking
4ºIA local
Downloads pelo Flipters
0
Estrelas no GitHub
46 mil

Última versão: v0.8.8, de 28 de outubro de 2026

Sobre o Jan

O Jan é um aplicativo de desktop de código aberto, mantido pela Menlo Research, para conversar com modelos de linguagem que rodam no próprio computador. Vem com modelos da família Jan e baixa outros do Hugging Face pelo Hub integrado.

Usa os motores llama.cpp e MLX e funciona totalmente offline. Também se conecta a provedores na nuvem, como OpenAI, Anthropic e Gemini, aceita servidores MCP e oferece um servidor de API local compatível com a OpenAI.

Principais recursos

  • Modelos próprios da família Jan prontos para rodar localmente
  • Hub integrado para baixar modelos do Hugging Face
  • Servidor de API local compatível com a OpenAI
  • Suporte a servidores MCP e busca na web
  • Conexão opcional com OpenAI, Anthropic, Gemini, Groq e outros

Arquivos para baixar

Instaladores publicados pelo fabricante, separados por sistema. Na dúvida, use o botão principal: ele leva à página oficial de download.

Windows
ArquivoVersãoTamanhoBaixar
Windows (arm64) .exeJan_0.8.8_arm64-setup.exev0.8.8320 MBBaixar Windows (arm64) .exe
Windows (x64) .exeJan_0.8.8_x64-setup.exev0.8.8545 MBBaixar Windows (x64) .exe
macOS
ArquivoVersãoTamanhoBaixar
macOS (universal) .dmgJan_0.8.8_universal.dmgv0.8.8111 MBBaixar macOS (universal) .dmg
macOS (universal) .zipjan-mac-universal-0.8.8.zipv0.8.8110 MBBaixar macOS (universal) .zip
Linux
ArquivoVersãoTamanhoBaixar
Linux (x64) .appimageJan_0.8.8_amd64.AppImagev0.8.8680 MBBaixar Linux (x64) .appimage
Linux (x64) .debJan_0.8.8_amd64.debv0.8.81.014 MBBaixar Linux (x64) .deb

Novidades

Novidades da versão v0.8.8Publicada em 28 de outubro de 2026. Notas do GitHub, em inglês.Mostrar

Jan v0.8.8: security fixes, llama.cpp 0.7.0, and Trusted Hosts for the local API

A security update to v0.8.7. We recommend updating. Your data and settings carry over; a few behaviours change, listed under What you might notice.

Security

  • Links in chat open in your browser. Links in model replies, tool results, model cards and release notes now always open in your system browser, never inside Jan's window. Links that aren't web or email links are shown as plain text.
  • The local API server checks where browser requests come from. A web page can only call it if its origin is trusted: the same machine, Jan itself, or a host you list in Trusted Hosts. Requests without a browser origin (SDKs, scripts, curl, Claude Code) work as before.
  • Server-side tool execution stays opt-in for every endpoint. Requests to the local API run MCP tools only when Settings > Local API Server allows server-side tool execution.
  • Paths are checked before Jan reads or writes them. Thread and assistant ids, and the file operations extensions use, stay inside Jan's data folder.
  • The Claude Code integration writes your shell profile safely. Values are quoted, unusual variable names are refused, and Jan's lines are kept in one marked block that Reset removes completely without touching your own lines.
  • The agent's file tools no longer follow a link out of their workspace, and folders such as your home, credentials and startup folders can't be attached as writable.
  • Windows: Jan runs system tools from the Windows system folder, and sign-in links are opened without going through cmd.
  • MCP sign-in only uses web addresses (http/https) for its endpoints.

What you might notice

  • Trusted Hosts for browser-based clients. A web app on another machine (for example Open WebUI's direct connection) or a browser extension calling Jan's API needs its host added to Settings > Local API Server > Trusted Hosts. Entries can include a scheme, so app://obsidian.md works for Obsidian plugins (thanks to @SnowingFox, #8608). Pages without a normal origin (local files, sandboxed frames) can be allowed by listing file:// or null.
  • The CORS switch now takes effect, and it starts on after updating. In earlier versions it was shown but had no effect.
  • Custom environment variables for Claude Code: keys that change how programs are found (PATH, PATHEXT, SystemRoot, ComSpec, LD_*, DYLD_*, JAN_* and the GPU runtime paths Jan uses) are refused with a message. Other variables, including NODE_OPTIONS, save as before.
  • Moving the data folder to a system folder, your home folder itself or a drive root (for example D:\) is refused; choose a folder such as D:\Jan.
  • MCP servers whose sign-in endpoints aren't web addresses now show a sign-in error.

New

llama.cpp engine 0.7.0.

The bundled engine moves from 0.5.0 to 0.7.0 (b11669). New per-model settings: an MoE expert GPU cache for mixture-of-experts models, Probabilistic draft sampling and Draft batch size for speculative decoding. They default to the engine's own defaults, so nothing changes unless you set them. Saved prompt caches from the previous engine are discarded once and rebuilt. (#9399)

Fixes

Local models failed to load on Windows when the user name had non-English characters (for example Cyrillic). (#9418)

With an HTTP proxy configured, documents with "Use embeddings" failed, because Jan's requests to its own engine went through the proxy. They now go direct; remote providers still use the proxy. (#9353)

An attachment was sent again on every turn, adding a copy per message and defeating the prompt cache. It's now included once per request. Thanks to [@yaodong-shen](htt

Ver a versão no GitHub

Avaliações de quem usa

Ainda sem avaliações

Usou o Jan? Conte para quem está escolhendo.

Avalie o Jan

Sua nota (obrigatória)

De 20 a 3.000 caracteres.0/3.000

Alternativas ao Jan

  • LM Studio

    Element Labs, Inc. · Rodar IA no seu computador

    App de desktop para baixar e rodar modelos de linguagem no PC, com chat e API local

  • GPT4All

    Nomic, Inc. · Rodar IA no seu computador

    Chatbot de IA local que roda modelos abertos em computadores comuns, sem exigir GPU

    • 77,3 mil no GitHub
  • Ollama

    Ollama Inc. · Rodar IA no seu computador

    Baixa e roda modelos de linguagem abertos no computador, por app, terminal ou API local

    • 187,8 mil no GitHub
  • Msty Studio

    CloudStack, LLC · Rodar IA no seu computador

    Espaço de trabalho de IA que reúne modelos locais e online em um único app de desktop

Ver todos em Rodar IA no seu computador

Fontes

Ficha escrita pela redação do Flipters a partir das fontes acima, revisada em 20 de novembro de 2026. Preços e versões mudam: confira no site oficial antes de comprar. Como trabalhamos.