OpenClaw logo

OpenClaw

Activo

Self-hosted, MIT-licensed AI assistant you message from the chat apps you already use

Condicional

OpenClaw is a credible free way to run a personal AI agent on your own hardware: MIT licensed, no paid tier, reachable from 29 chat channels, and able to browse, read and write files and run shell commands. Conditional because that reach is the risk: its docs disclaim it as a boundary between mutually adversarial users, and Unit 42 found malicious ClawHub skills, warning that installing a skill grants complete control over the agent's identity. Right for technical users who will harden and audit it; wrong for unmanaged shared deployments.

IA nativa

A self-hosted gateway routes chat messages to an AI agent that browses the web, reads and writes files, and runs shell commands

¿Es adecuada para ti?

Bueno para

  • Running a personal AI agent on hardware you control: the README says state, memory and credentials live on your hardware, and the site says state lives on your machine, not a vendor cloud
  • Talking to an agent from apps you already use, with openclaw.ai naming WhatsApp, Telegram, Discord, Slack, Signal and iMessage among its 29 channels, in DMs and group chats
  • Choosing your own model provider, from Anthropic, OpenAI, Google and DeepSeek to local runtimes such as Ollama, LM Studio, llama.cpp and vLLM
  • Zero software cost: MIT licensed, stewarded by an independent 501(c)(3), with no paid tier, hosted service or token
  • Hands-on computer errands, which OpenClaw's site describes as browsing the web, filling forms, reading and writing files and running shell commands
  • Starting from restrictive defaults: on a regular host install the gateway binds to loopback, most channels answer unknown DM senders with a pairing code, and group access is allowlisted, with an openclaw security audit command to detect drift

No recomendado para

  • Sharing one agent or gateway between people who do not trust each other: the security docs state OpenClaw is not a hostile multi-tenant security boundary for mutually adversarial users
  • Installing community skills without auditing them: Unit 42 identified five malicious skills on ClawHub that had not been blocked between February and May 2026, and warns that installation results in complete control over the agent's identity; OpenClaw deleted all five after Unit 42 reported them
  • Deployments nobody will keep patched: CVE-2026-25253, rated 8.8 High, let versions before 2026.1.29 take a gatewayUrl from a query string and open a WebSocket connection without prompting, sending a token
  • Non-technical users: installation runs through a shell script, PowerShell or npm and requires Node 24.16.0+ or 26.1.0+, with 24.22.1+ or 26.12.1+ strongly recommended
  • Anyone who wants a vendor-hosted service, since the README states the project has none

Nuestra experiencia

We haven't tested OpenClaw ourselves. This profile is based on public documentation, user reviews, and community feedback.

Precios

Código abierto
Open source (MIT)$0
  • No subscription, no hosted tier, no token
  • Bring hosted, subscription-backed, gateway or local models
  • Uses an API key from your chosen model provider
  • Prepared cloud workers incur provider running-machine charges until deleted
Ver precios completos

Recetas de flujo de trabajo

Install and harden a personal gateway

Get OpenClaw running on your own machine before connecting anyone else

  1. Install with curl -fsSL https://openclaw.ai/install.sh | bash on macOS, Linux or WSL2, iwr -useb https://openclaw.ai/install.ps1 | iex on Windows, or npm install -g openclaw@latest --allow-scripts=openclaw (omit --allow-scripts on npm 11.15 and earlier)
  2. Add an API key from your chosen model provider
  3. Read the security guide, exposure runbook and sandboxing guide before connecting other users
  4. Apply a hardened baseline config that keeps the gateway local, paired and tool-restricted
  5. Run openclaw security audit to check the deployment has not drifted

Aún no hay cambios de veredicto

El reloj corre desde el primer día: los cambios aparecerán aquí a medida que evolucione nuestro veredicto.

Registro de verificación

  • Contenido· Actualizado

    Agente automatizado

    README Node requirement is 24.16.0+ on 24.x or 26.1.0+, with 24.22.1+/26.12.1+ strongly recommended (stored said required 24.22.1+/26.12.1+). Latest release v2026.11.3 (Nov 10), extended-stable v2026.9.37; 394.4k stars. MIT and no paid tier unchanged.

  • Contenido· Actualizado

    Agente automatizado

    README Node requirement is now 24.22.1+ or 26.12.1+ (Node 26 recommended), stored 24.16+ or 26.1+; removed the dated version and star stamp from the description. CVE-2026-25253 (8.8 High, before 2026.1.29) and Unit 42 (five malicious ClawHub skills, deleted) re-confirmed against the CVE record and Unit 42 page. Still MIT, 29 channels, no paid tier.

  • Perfil· Sin cambios

    Agente automatizado

  • Perfil· Sin cambios

    Agente automatizado

  • Perfil· Requiere atención

    Agente automatizado

    Release dates from the fetched page were unreliable (year garbled), so the stored v2026.9.4 stamp and 389.4k stars could not be confirmed. Stored values kept.

Cómo evaluamos

¿La quieres funcionando en tu empresa?

Hemos probado esta herramienta y construimos con herramientas así cada día. Cuéntanos el flujo de trabajo y la instalamos, la integramos y te la entregamos funcionando.

La conversación funciona con Gnosari, una de las herramientas de este directorio. Una conversación real, no un guion de ventas.