Português (Brasil)

Os melhores agentes de IA de código aberto e assistentes pessoais de IA

Sete agentes de IA de código aberto comparados por licença, comunidade, maturidade e abertura real, de OpenClaw e Hermes Agent a códigos pequenos que dá para ler.

Resumo

Resumo
BotLicençaApps de chat
OpenClawMIT394,2 milSimNãoTelegram, WhatsApp, iMessage, Discord, SlackGrátis
Hermes AgentMIT261,7 milSimNãoTelegram, WhatsApp, iMessage, Discord, SlackA partir de US$ 20/mês
nanobotMIT49,9 milSimNãoTelegram, WhatsApp, Discord, SlackGrátis
ZeroClawMIT OR Apache-2.033,3 milSimSimTelegram, WhatsApp, DiscordGrátis
Agent ZeroMIT19,8 milSimSimTelegram, WhatsAppGrátis
RakazoApache-2.07,5 milSimSimTelegram, WhatsApp, iMessage, SlackA partir de US$ 10/mês
NanoClawMIT31,1 milSimSimTelegram, WhatsApp, iMessage, Discord, SlackGrátis
Estrelas no GitHub em 8 de nov. de 2026

Checklist

Checklist
OpenClawHermes AgentnanobotZeroClawAgent ZeroRakazoNanoClaw
Licença open sourceSimSimSimSimSimSimSim
Roda modelos locaisSimSimSimSimSimSimSim
Sandbox por padrãoNãoNãoNãoSimSimSimSim
Sem telemetria por padrãoNãoSimSimSimNãoSimNão
Vive nos seus apps de chatSimSimSimSimSimSimSim
Trabalha enquanto você está foraSimSimSimSimSimSimSim

“Código aberto” abrange muita coisa nesta categoria. Alguns projetos têm licença MIT e nenhuma empresa vendendo nada por cima; outros são código aberto ao lado de um serviço hospedado pago; alguns são abertos, mas mal recebem manutenção. Este ranking trata da parte de código aberto: o que a licença permite que você faça, quem está por trás do código e se o projeto ainda vai estar avançando no ano que vem.

Como classificamos

Os sete são de código aberto e auto-hospedáveis, e todos rodam com modelos locais. Avaliamos:

  • Licença. Licenças permissivas (MIT, Apache-2.0) ficam acima do copyleft para a maioria dos leitores, porque você pode modificar e redistribuir sem compartilhar suas alterações.
  • Independência. Uma organização sem fins lucrativos ou um laboratório de pesquisa sem nada para vender é uma garantia mais forte do que um fornecedor cujo código aberto alimenta um plano pago, embora nenhum dos dois seja um problema por si só.
  • Comunidade e maturidade. Tamanho do projeto, ritmo de lançamentos e se os mantenedores o chamam de alfa, beta ou estável.
  • Facilidade de modificar. Quanto código você precisa ler para mudar alguma coisa.
  • O checklist do site (tabela acima): sandbox, telemetria, apps de chat e trabalho em segundo plano continuam contando, só que com menos peso do que no nosso ranking de agentes auto-hospedados.

Deixamos de fora o Khoj, que é AGPL-3.0 e não tem nenhum lançamento desde março de 2026, e o OpenFang, que não tem commits desde maio de 2026.

1. OpenClaw

O OpenClaw é o agente de IA de código aberto padrão por um motivo. Tem licença MIT, não tem plano pago nem serviço hospedado e é mantido pela organização sem fins lucrativos OpenClaw Foundation (página inicial). É também, com folga, a maior comunidade desta lista (veja a tabela), com 142 plugins oficiais e um grande ecossistema de skills.

Código aberto não significa seguro por padrão: o sandbox vem desativado e uma verificação diária de atualizações vem ativada. Leia O OpenClaw é seguro? antes de conectá-lo a contas reais, e o que é o OpenClaw se você está começando agora.

WhatsApp chat with an OpenClaw assistant giving casual travel advice to a user in Marrakech
Chatting with OpenClaw in WhatsAppdocs.openclaw.ai

2. Hermes Agent

O Hermes Agent tem licença MIT e é o segundo maior projeto aqui. É o mais aberto em relação a dados entre os dois grandes: sem telemetria por padrão, e tudo fica em ~/.hermes, a menos que você escolha o Nous Portal como provedor de modelos. Seu recurso de destaque é escrever e refinar as próprias skills reutilizáveis.

Fica em segundo em independência: a Nous Research vende assinaturas do Nous Portal a partir de US$ 20 por mês junto com o código gratuito. Você nunca precisa de uma, mas busca na web, imagens e voz hospedadas exigem um plano ou suas próprias chaves. Mais em o que é o Hermes Agent.

Hermes Agent web dashboard Sessions page listing live sessions from cron, Discord, Telegram and the CLI, with rename, export and delete actions
Hermes Agent's dashboard showing sessions across chat platformshermes-agent.nousresearch.com

3. nanobot

O nanobot vem do Data Intelligence Lab da Universidade de Hong Kong e foi feito para ser lido: um núcleo pequeno em Python, licença MIT e nenhum serviço hospedado para vender. Ele tem um SDK em Python e uma API compatível com OpenAI, então também serve de base para o seu próprio agente. A WebUI incluída é uma das melhores da lista.

A contrapartida é que os comandos de shell não rodam em sandbox por padrão.

nanobot WebUI new-topic screen with Apps, Skills, Automations and Channels in the sidebar, project-grouped topics, and a composer with permission and microphone controls
nanobot's bundled browser WebUIgithub.com

4. ZeroClaw

O ZeroClaw tem licença dupla MIT ou Apache-2.0 e é distribuído como um único binário em Rust. Só pelo checklist, ele supera todos os anteriores: sandbox por padrão e sem telemetria. Fica em quarto aqui porque sua comunidade é bem menor que a do OpenClaw e a do Hermes Agent, e Rust é uma barreira maior do que Python ou TypeScript se você pretende alterar o código.

ZeroClaw homepage headline: The personal AI agent you actually own, one lightweight Rust binary on your machine with your keys or your local models
ZeroClaw's homepagezeroclaw.com

5. Agent Zero

O Agent Zero tem licença MIT e é o projeto mais antigo deste ranking, com lançamentos desde junho de 2024 e as versões v2.11 a v2.15 publicadas entre o fim de agosto e o início de novembro de 2026. Seu Plugin Hub da comunidade tem mais de 200 plugins.

Duas coisas para saber sobre a organização: é uma pequena empresa tcheca, e o projeto opera um proxy de modelos com staking de tokens para quem tem o seu criptotoken A0T (detalhes). Você pode ignorar esse proxy e usar qualquer provedor ou modelo local.

Agent Zero web UI showing a request to write a kickoff plan, the agent's collapsed steps for writing and verifying the file in the terminal, and a summary table of the plan
Agent Zero completing a first task in its web UIgithub.com

6. Rakazo

O Rakazo, que nós desenvolvemos, é Apache-2.0 e totalmente auto-hospedável. O código aberto fica ao lado de planos hospedados pagos que adicionam um computador na nuvem, então em independência ele está na mesma posição que o Hermes Agent. Cumpre todos os itens do checklist, mas é mais novo e se define como beta. Veja a análise do Rakazo.

Rakazo web app with a chat with a bot called Chief and a side panel showing the bot's live browser screen, a Take control button and routines
A Rakazo bot chat with its computer screen beside itgithub.com

7. NanoClaw

O NanoClaw tem licença MIT e um código deliberadamente minúsculo: um processo host e um punhado de arquivos. Isso o torna o agente mais legível da lista. Fica em último em abertura porque é construído sobre o Claude Agent SDK da Anthropic e espera o Claude Code para toda personalização, então na prática fica preso a uma ferramenta proprietária, mesmo que outros provedores possam ser adicionados por agente.

NanoClaw setup wizard in a terminal explaining that the assistant lives in its own sandbox and asking whether to fetch a hardened image or build it locally
NanoClaw's setup wizard choosing the agent's sandbox imagedocs.nanoclaw.dev

Licenças em resumo

Licença Agentes
MIT OpenClaw, Hermes Agent, nanobot, Agent Zero, NanoClaw
MIT ou Apache-2.0 ZeroClaw
Apache-2.0 Rakazo

Todas permitem executar, modificar e redistribuir o código, inclusive para fins comerciais. O modelo que você conecta é outra história: modelos locais de pesos abertos têm suas próprias licenças, e provedores hospedados, seus próprios termos.

Para outros ângulos, veja os melhores agentes de IA locais e as alternativas ao OpenClaw.

Melhores escolhas

  1. OpenClaw

    Grátis

    Free, MIT-licensed personal AI agent that runs on your own computer and takes orders from WhatsApp, Telegram, iMessage, Slack and 20+ other chat apps.

    The biggest ecosystem and every chat app, but sandboxing is off and telemetry is on by default.

    Pontos fortes

    • Free and MIT licensed, with no paid tier
    • Runs on your own hardware, and state, memory and credentials stay there
    • Works in 29 chat channels, including WhatsApp, Telegram, iMessage, Slack, Discord and Microsoft Teams
    • Model-agnostic: 64 model and media providers, plus local models
    • Large ecosystem of skills and 142 official plugins, and very active development

    Pontos fracos

    • Model costs are on you and can run high: testers and users have reported spending over $100 in a day with expensive models
    • Sandboxing is off by default and the agent can run commands on the host unless you turn on approvals
    • Setup and upkeep expect comfort with the command line; maintainers warn it is risky for non-technical users
    • Broad access to email, messages and the system makes prompt injection and malicious third-party skills a real risk
    Acessar OpenClaw

  2. Hermes Agent

    A partir de US$ 20/mês

    Free, MIT-licensed AI agent from Nous Research that runs on your own machine or server, learns reusable skills, and chats with you on Telegram, Slack and more.

    MIT licensed, no telemetry and lives in your chat apps, but commands aren't sandboxed by default.

    Pontos fortes

    • Free and MIT licensed, and runs on hardware you control
    • Writes and refines its own skills from experience, on top of persistent memory and cross-session search
    • One gateway for 20+ chat platforms, including Telegram, Discord, Slack, WhatsApp, Signal and email
    • Run several separate agents as profiles, each with its own model, memory and skills, and let them talk in group chats
    • Model-agnostic, with a one-command import from OpenClaw

    Pontos fracos

    • Setup expects comfort with the command line and with running your own server
    • Model costs are on you unless you use free models, and hosted web search, images and speech need a paid Nous Portal plan or your own keys
    • iMessage needs a separate BlueBubbles server on a Mac
    • No native mobile app; Android support is a command-line install through Termux
    Acessar Hermes Agent

  3. nanobot

    Grátis

    Free, MIT-licensed personal AI agent in Python with a browser UI and terminal app, scheduled tasks, memory, and chat on Telegram, Discord, Slack and more.

    Small, readable Python with a good web UI and no telemetry, but shell commands aren't sandboxed by default.

    Pontos fortes

    • Free and MIT licensed, with a small Python core that is meant to be read and modified
    • Polished bundled WebUI with projects, file diffs, an MCP app catalog and an automations calendar, plus a terminal UI
    • Many chat channels, including Telegram, Discord, Slack, WhatsApp, WeChat, Feishu, Teams, Matrix and email
    • Scheduled automations, long-running goals and a heartbeat that reports only useful results to your last chat
    • Works with local models through Ollama, vLLM or LM Studio

    Pontos fracos

    • Shell commands are not sandboxed by default; the bubblewrap or macOS Seatbelt sandbox must be turned on, and Windows has none
    • Model costs are on you, and voice messages need a separate transcription provider such as Groq or OpenAI
    • No native mobile or desktop app; on a phone you use the WebUI in a browser or a chat app
    • Missed scheduled runs are not replayed and interrupted subagent tasks are not relaunched after a restart
    Acessar nanobot

  4. ZeroClaw

    Grátis

    Personal AI agent in one Rust binary, MIT or Apache-2.0, with local or cloud models, 30+ channels, approval gates and an OS sandbox on by default.

    Meets every check: one Rust binary, approval gates and an OS sandbox on by default, no telemetry, local models.

    Pontos fortes

    • Safe defaults: the recommended profile asks before medium-risk actions, blocks high-risk ones, keeps files in the workspace and runs tools in an OS sandbox
    • One small Rust binary with one config file, running on macOS, Linux, Windows and boards like a Raspberry Pi
    • More than 30 channels, plus a web dashboard for chat, memory, config and cron
    • Provider fallback chains, local models through Ollama, and cryptographic receipts for tool calls
    • States plainly that it sends no telemetry and needs no cloud account or license server

    Pontos fracos

    • Slack, iMessage, Signal and several other channels are not in the standard release; you build from source with extra features to get them
    • `zeroclaw quickstart` only sets up the model provider; channels and risk profiles mean editing the TOML config file
    • The Docker sandbox backend isn't picked automatically under the default native runtime
    • Model costs are on you
    Acessar ZeroClaw

  5. Agent Zero

    Grátis

    Free, MIT-licensed AI agent that runs in its own Docker Linux workspace with a terminal, browser and desktop apps, and chats on Telegram and WhatsApp.

    Runs in its own Docker container with local models, but sends telemetry by default.

    Pontos fortes

    • Free and MIT licensed, with frequent releases (v2.11 to v2.15 between late August and early November 2026)
    • The agent works in its own Linux workspace with a terminal, browser, desktop apps and LibreOffice, isolated from your computer unless you grant host access
    • Web search runs through a local SearXNG instance, and speech-to-text and text-to-speech can run locally
    • Projects keep memory, files, secrets, instructions and model choices separate per job, with workspace snapshots you can roll back
    • Built-in Telegram, WhatsApp and email channels, a scheduler, MCP and a community Plugin Hub with 200+ plugins

    Pontos fracos

    • Needs Docker, and the container image is a full Linux desktop environment rather than a small service
    • No built-in image generation; the docs show teaching it an image API yourself
    • By default it checks for updates with Agent Zero's server, sending your version and a hashed instance ID
    • Code runs in the same container as Agent Zero itself today; per-task sandboxes are only a v3 prototype
    • WhatsApp works by linking a phone account through a Baileys bridge, which needs Node.js, rather than the official WhatsApp Business API
    Acessar Agent Zero

  6. Rakazo

    A partir de US$ 10/mês

    Open-source, self-hostable platform for persistent AI bots that each get a job, a computer, memory and routines, using the model you choose.

    Our own product. Meets every check: Apache-2.0, sandboxed bot computers, no telemetry by default, any model you connect.

    Pontos fortes

    • Open source (Apache-2.0) and fully self-hostable, including with local models
    • Choice of model per bot, including existing Claude or ChatGPT subscriptions
    • Bots keep working on schedules and triggers with their own cloud computer
    • Approval controls over which actions a bot may take on its own

    Pontos fracos

    • Still in beta, with frequent releases
    • You supply and pay for the model on the hosted plans, unless you buy Rakazo credits
    • Telegram, WhatsApp and iMessage/SMS are only available when self-hosted
    • More setup than a single chat app
    Acessar Rakazo

  7. NanoClaw

    Grátis

    Small, MIT-licensed OpenClaw alternative that runs each agent in its own Docker container and chats with you on WhatsApp, Telegram, Slack, Discord and more.

    Every agent in its own container and a tiny codebase, but tied to Claude Code and sends setup diagnostics by default.

    Pontos fortes

    • Every agent runs in its own Docker container and sees only the folders you mount, so shell access stays off your host
    • Small codebase (one host process and a handful of files) that you customize by having Claude Code edit your fork
    • Agents never hold raw API keys: outbound calls go through a credential gateway with per-agent policies and rate limits
    • Many chat channels, including WhatsApp, Telegram, Slack, Discord, iMessage, Teams, Matrix and email, with one or several agents per channel
    • Scheduled tasks with optional script gates that skip waking the agent when there's nothing to do

    Pontos fracos

    • Built around Claude and Claude Code: customizing, debugging and adding channels all go through Claude Code
    • Sends anonymous setup diagnostics unless you set NANOCLAW_NO_DIAGNOSTICS=1
    • No config files by design, so every change means editing code in your own fork
    • Needs Docker, and Windows only works through WSL2
    Acessar NanoClaw

Recursos

Recursos
OpenClawHermes AgentnanobotZeroClawAgent ZeroRakazoNanoClaw
Busca na webSimSimSimSimSimSimSim
Geração de imagensSimSimSimSimNãoSimDesconhecido
Modo de vozSimSimSimSimSimSimDesconhecido
Envio de arquivosSimSimSimSimSimSimSim
MemóriaSimSimSimSimSimSimSim
Executa tarefas por vocêSimSimSimSimSimSimSim
Integrações com appsSimSimSimSimSimSimSim
Trabalha sozinhoSimSimSimSimSimSimSim
Manda mensagem primeiroSimSimSimSimSimSimSim
Vários botsSimSimSimSimSimSimSim

Fontes

OpenClaw

  1. OpenClaw homepage and Foundation section
  2. OpenClaw integrations: channels, providers and plugins
  3. openclaw/openclaw on GitHub (MIT, v2026.11.1)
  4. OpenClaw docs: Sandboxing (off by default)
  5. Wikipedia: OpenClaw
  6. Notebookcheck: OpenClaw can burn through hundreds of dollars per day
  7. OpenClaw docs: Memory overview
  8. OpenClaw docs: Automations
  9. OpenClaw docs: Chat channels
  10. OpenClaw docs: iMessage
  11. OpenClaw docs: Heartbeat, now a default Proactive check job
  12. OpenClaw docs: Multi-agent routing
  13. OpenClaw docs: Platforms (macOS, Windows, Linux, iOS and Android apps)
  14. OpenClaw docs: Tools (exec, browser, web search)
  15. OpenClaw docs: Audio and voice notes (inbound transcription)
  16. OpenClaw docs: Image and media support (inbound media)
  17. OpenClaw docs: Install (system requirements, installer script, npm, desktop apps, Docker)
  18. OpenClaw docs: One-click deploy on Railway
  19. OpenClaw docs: Usage telemetry and update checks (on by default, feature statistics opt-in)
  20. OpenClaw docs: Ollama provider (local models)

Hermes Agent

  1. NousResearch/hermes-agent on GitHub (MIT, v0.23.0)
  2. Hermes Agent homepage and Nous Portal pricing
  3. Hermes Agent documentation
  4. Hermes Agent docs: Profiles, running multiple agents
  5. Hermes Agent docs: Bot Mode
  6. Hermes Agent docs: Voice mode
  7. Hermes Agent docs: Vision and image paste
  8. Hermes Agent docs: iMessage via BlueBubbles
  9. Nous Research on X: Meet Hermes Agent (February 25, 2026)
  10. Hermes Agent docs: Session heartbeats and cron watchdogs
  11. Hermes Agent docs: FAQ (Is my data sent anywhere?)
  12. Hermes Agent docs: Installation (desktop packages, install script, Docker)
  13. Hermes Agent docs: Platform support (no Linux desktop package; PyPI installs unsupported)
  14. Hermes Agent docs: Docker setup
  15. Hermes Agent docs: Configuration (terminal backend defaults to local)
  16. Hermes Agent docs: Security (approval modes, optional container isolation)
  17. Hermes Agent docs: Local models
  18. Hermes Agent example config (shared metrics off by default)

nanobot

  1. HKUDS/nanobot on GitHub (MIT, v0.4.1, README)
  2. nanobot documentation
  3. nanobot release archive (officially launched February 2, 2026)
  4. nanobot docs: Chat apps
  5. nanobot docs: Providers and models (Ollama, vLLM, LM Studio)
  6. nanobot docs: Configuration (security, exec sandbox off by default, transcription, Langfuse)
  7. nanobot docs: Automations and heartbeat
  8. nanobot docs: Concepts (heartbeat delivery, subagent recovery)
  9. nanobot docs: Memory and Dream
  10. nanobot docs: Multiple instances
  11. nanobot docs: Deployment (Docker, services, Render)
  12. nanobot source: skills installer runs with DISABLE_TELEMETRY

ZeroClaw

  1. zeroclaw-labs/zeroclaw on GitHub (MIT OR Apache-2.0, v0.8.7, README)
  2. ZeroClaw website
  3. ZeroClaw docs: Sandboxing
  4. ZeroClaw source: risk presets (Balanced, recommended, has the sandbox on)
  5. ZeroClaw docs: Channels overview (default and standard release bundles)
  6. ZeroClaw docs: You own it (no telemetry)
  7. ZeroClaw docs: Docker and containers
  8. ZeroClaw source: tools (image generation, screenshot, web)

Agent Zero

  1. agent0ai/agent-zero on GitHub (MIT, README, safety model)
  2. Agent Zero releases (v0.2 in June 2024 to v2.15 on November 1, 2026)
  3. Agent Zero homepage
  4. Agent Zero docs: Installation (Launcher, A0 Install, Docker, local models)
  5. Agent Zero docs: VPS deployment (hardware requirements)
  6. Agent Zero model provider list
  7. Agent Zero update check code (version and hashed ID sent to api.agent-zero.ai)
  8. Agent Zero built-in Telegram integration plugin
  9. Agent Zero built-in WhatsApp integration plugin
  10. Agent Zero built-in plugins (scheduler, notify user, email, SearXNG search, Whisper STT, Kokoro TTS)
  11. Agent Zero docs: Memory guide
  12. Agent Zero docs: Agent Profiles
  13. Agent Zero docs: API integration (adding image generation yourself)
  14. Agent Zero v3: A Sneak Peek Inside the Sandbox (August 17, 2026)
  15. Agent Zero LLM API (Venice.ai proxy for A0T token stakers)

Rakazo

  1. Rakazo homepage
  2. Rakazo pricing
  3. Rakazo privacy policy
  4. Rakazo on GitHub (README and license)
  5. Rakazo changelog
  6. Rakazo releases
  7. Rakazo docs: Image and video generation
  8. Rakazo docs: Memory
  9. Rakazo docs: Connect apps
  10. Rakazo docs: Routines
  11. Rakazo docs: Chat apps
  12. Rakazo docs: Messaging apps (self-hosting)
  13. Rakazo docs: Bots and chats (add another bot, bot templates)
  14. Rakazo docs: Groups (several bots in one chat)
  15. Rakazo docs: Mobile app (notifications)
  16. Rakazo privacy policy (updated Sep 14, 2026)
  17. Rakazo privacy policy source on GitHub
  18. Rakazo docs: Logs and monitoring (product analytics off by default)
  19. Rakazo docs: Desktop app (run locally in Docker, updates)
  20. Rakazo docs: Docker computers
  21. Rakazo docs: Self-hosted models (Ollama, LM Studio)
  22. Rakazo Railway template setup guide

NanoClaw

  1. nanocoai/nanoclaw on GitHub (MIT, README: containers, channels, diagnostics, requirements, models FAQ)
  2. NanoClaw website
  3. NanoClaw docs: Quickstart
  4. NanoClaw docs: Echo hardened runtime
  5. NanoClaw skills: channel, Ollama, OpenCode and Codex installers