OpenHuman

What is OpenHuman?

OpenHuman is a free, open-source personal AI from TinyHumans that runs as a desktop app on macOS, Windows and Linux. Its memory engine chooses what to retain, how to compress it and what to bring forward when an agent needs context, and that memory stays on your own machine. A workflows engine orchestrates one or many agents to automate tasks, and OAuth, MCP servers and skills connect it to apps such as Gmail, Slack, Notion, Telegram, Teams, GitHub and spreadsheets. It is licensed under GPL-3.0, so the software costs nothing, while a TinyHumans key unlocks managed inference, search, embeddings and integrations; you can instead bring your own providers, including local models. TinyHumans credits are sold as Basic at $20/month, Pro at $200/month, custom Enterprise, or pay as you go with top-ups from $5. Developers can also use it as a Rust library.

Use cases

• Run a personal AI that remembers your work
• Automate tasks across Gmail, Slack and Notion
• Orchestrate several agents with workflows
• Run local models with private memory
• Embed an agent harness in a Rust project

Who it's for

• Power users
• Privacy-minded individuals
• Developers
• Automation builders

Why use OpenHuman

• The software is free and open source, so you only pay if you want managed model access.
• Local-first memory keeps what the assistant learns about you on your own machine.
• One app connects chat, email, docs and code tools, so an agent can act across them instead of only replying.
• You can point it at local or existing providers and avoid vendor lock-in.
• Credits cost the same per call whether you subscribe or pay as you go, so there is no forced plan.

OpenHuman features

• Desktop app for macOS, Windows and Linux
• Memory engine that decides what to keep and compress
• Local-first storage for the memory it builds about you
• Workflow engine for single or multi-agent automations
• OAuth app connections, MCP servers and skills
• Bring your own providers, including models on your own machine
• Managed inference, search and embeddings through a TinyHumans key
• Rust library for developers
• GPL-3.0 source on GitHub

OpenHuman integrations

• Notion
• Gmail
• Telegram
• Slack
• Excel
• GitHub

How to get started with OpenHuman

1. Download the desktop build for your operating system from the OpenHuman page.
2. Add a TinyHumans key for managed access, or point it at your own model providers.
3. Connect apps through OAuth, MCP servers and skills.
4. Let the memory engine build context about your work as you use it.
5. Describe a task or build a workflow, and the engine orchestrates agents to carry it out.

OpenHuman limitations

• A TinyHumans key is needed for managed inference, search, embeddings and integrations
• Model calls go to the provider you choose, so data leaves your machine unless you use local models
• TinyHumans sales are final, and subscription payments and credits are non-refundable

OpenHuman pricing

Yes, OpenHuman has a free plan. Paid plans start at $20 per month, according to the official pricing page on 24 Oct 2026.

OpenHuman plans

• Basic

  $20/month

  or $200/yr billed annually

  • $21 of credits every month
  • 1 OpenCompany company, up to 3 users
  • 1 GB of memory storage
  • Free memory inference

• Pro

  $200/month

  or $2,000/yr billed annually

  • $210 of credits every month
  • 5 OpenCompany companies, unlimited users
  • Higher rate limits
  • 20 GB of memory storage

• Enterprise

  Custom

  • Unlimited companies and custom usage
  • On-premise deployment
  • SSO / SAML and dedicated onboarding
  • Priority support

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

OpenHuman alternatives

The main OpenHuman alternatives listed on Debuly are OpenClaw, Open WebUI, Jan, Msty, BrowserOS and AutoGPT. The table compares pricing and platforms; order is A–Z.

1. 

   AutoGPT

   Agent platform with a plain-English AutoPilot, a visual workflow builder and self-hosting, plus a $50/month Pro plan with a 7-day trial.

   Automation and agentsDeveloper platformsProductivity
   FreemiumVisit AutoGPT (official site)
2. 

   BrowserOS

   Free, open-source Chromium browser with built-in AI agents and an MCP server, so agents like Claude Code or Codex can browse as you.

   Automation and agentsProductivityDeveloper platforms
   Open sourceVisit BrowserOS (official site)
3. 

   Jan

   Free, open-source desktop AI assistant that runs models offline on your computer or connects to cloud models with your own keys.

   Chat assistantsDeveloper platforms
   Open sourceVisit Jan (official site)
4. 

   Msty

   Privacy-first AI workspace for chatting with local and online models, with a model gateway, agents and knowledge stacks.

   Chat assistantsAutomation and agentsDeveloper platforms
   FreemiumVisit Msty (official site)
5. 

   Open WebUI

   Self-hosted AI chat platform for Ollama and OpenAI-compatible models with RAG, agents, tools, notes, channels and role-based access.

   Chat assistantsDeveloper platformsAutomation and agents
   Open sourceVisit Open WebUI (official site)
6. 

   OpenClaw

   Open-source personal AI assistant that runs on your own devices and takes actions for you through WhatsApp, Telegram, Slack, Discord and other chat apps.

   Automation and agentsChat assistantsProductivity
   Open sourceVisit OpenClaw (official site)

OpenHuman FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from tinyhumans.ai · fetched 23 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.