Recording intelligenceAI-generated brief · check the source for context

I am Switching to OpenHuman...

26:41 recording · AUTO · 1 speaker

Watch the original

Executive Summary AI
  • The host introduces OpenHuman as a brand new AI agent that installs as a normal desktop app rather than through the terminal like OpenClaw or Hermes, which he says kills those tools for about 90% of people; it hit number one on Product Hunt two weeks ago and has almost 30,000 GitHub stars.
  • Walking the GitHub repo, he notes it is built in Rust and TypeScript, ships an English, Chinese, Japanese, Korean and German readme, labels itself an early beta, keeps your memory and data local while routing model calls, search and OAuth through a hosted backend, and reaches 118 plus integrations by using Composio underneath.
  • After choosing the simple setup over custom API keys, he demonstrates what the agent does out of the box: deep web research, scraping, browser and computer control, writing code and running commands, a built-in cron scheduler, and 118 integrations whose triggers pass through a gatekeeper agent that drops, remembers, reacts or escalates.
  • He calls the memory system the part that earns the hype, inspired by Karpathy's Obsidian wiki workflow: everything connected is chopped into markdown files summarized by source, by topic and by day, readable and editable in a vault you open from Finder, refreshed by AutoFetch every 20 minutes and swappable for the open source agent memory backend.
  • Comparing the three harnesses he puts OpenHuman first on ease of install, notes OpenClaw's 375,000 stars and OpenAI and GitHub sponsorship, Hermes running on a five dollar VPS, then lists the rough edges: a Linux app image bug, a partially built MCP server, a shallow OneDrive integration, Ollama embedding crashes, and marketing that oversells local first.

Brief overview

OpenHuman is the first agent harness packaged as a double-click desktop app, winning on accessibility rather than power.

  1. Double-click install is the real innovationEvery rival harness is terminal-first; OpenHuman ships a .dmg you drag into Applications in about 30 seconds.
  2. Memory you can open and readThe vault is plain markdown summarized by source, topic and day, and their docs say you cannot trust a memory that you cannot read.
  3. Local first is only partly trueYour data stays on the machine, but the default install routes model calls, web search and OAuth through their hosted backend.

Questions this recording answers

10 questions, each answered where it is said
How do I install OpenHuman without touching the terminal?

Load tinyhumans.ai/OpenHuman and hit download. You get a .dmg, the standard Mac installer format, the same shape as downloading Slack or Notion. Drag OpenHuman into your Applications folder and open it. That is the entire install, maybe two steps, about 30 seconds.

Can OpenHuman actually attend a meeting on my behalf?

Yes. You drop a meeting link in and it joins as a real participant: it hears everybody on the call, takes notes in the background, and can speak with a voice in real time. The docs only show Google Meet right now, and he is wary of using it in real meetings.

Should I choose simple or custom when it asks how to run it?

Simple routes model calls, web search and integration OAuth through their backend: one subscription, every model included, no API keys, token juice automatic, plus a dollar of free credit. Custom means your own OpenAI, Anthropic, search and Composio setup, with more setup and more to go wrong. He recommends simple.

Where does OpenHuman keep its memory and can I read it?

Everything you connect, email, chats, documents, calendar, gets chopped into small markdown files, summarized by source, by topic, and one global summary per day. Go to Intelligence, the memory tab, click view folder, and Finder opens straight to your vault. You can edit the files or open the vault in Obsidian.

What is token juice and how much does it save?

A compression layer baked into OpenHuman that shrinks what is sent to the model, so you pay far less per call. They claim up to 80% token savings, though reviews he has seen measure closer to 70%. It is why OpenHuman can ship one subscription instead of bring your own API keys.

Is OpenHuman really local first?

Only partly. The memory of your data really does live on your machine, but the default install still routes model calls, web search and the OAuth handshakes through their hosted backend. Full self hosting is doable, swapping in Ollama for models, SearXNG for search and direct mode Composio, but it takes work.

How does it ship with 118 integrations out of the box?

It uses Composio underneath, so when you click connect Gmail you go through Composio's authentication flow. He calls that smart rather than a knock: they scale on day one instead of spending two years building 118 connectors themselves. Gmail, Slack, Notion, Drive, Linear and Calendar are all included.

What does the subconscious loop actually do?

Every five minutes the agent quietly wakes itself in the background, looks at the standing tasks you gave it and the state of your workspace, then picks one of three options: skip because nothing changed, act on its own, or escalate to you. Read only work runs silently, actions wait for approval.

What is still broken or rough in the current version?

On Linux the AppImage fails to launch on certain setups, so use the .deb package on Debian or Ubuntu. The MCP server is only partially built out, the OneDrive integration is shallow and not fully searchable, and the local model path through Ollama crashes on certain embedding requests.

Is OpenHuman better than OpenClaw or Hermes?

His verdict is that OpenHuman invents none of the mechanics except the meeting feature. Markdown memory already existed in Hermes, integrations and channels in OpenClaw. The real innovation is packaging: the most opinionated, most beginner friendly harness today. Not the most powerful agent, but by far the most accessible.

Key Quote

“which honestly kills it for about 90% of people.”

— I am Switching to OpenHuman..., at 0:26▶ watch at 0:26
Key Quote

“But OpenHuman, it is the first one in this category that literally anybody, even my mom, can actually run.”

— I am Switching to OpenHuman..., at 0:29▶ watch at 0:29
Key Quote

“This thing can attend a meeting on your behalf.”

— I am Switching to OpenHuman..., at 0:41▶ watch at 0:41
Key Quote

“I would be very weary of utilizing this inside of your meetings.”

— I am Switching to OpenHuman..., at 15:40▶ watch at 15:40
Key Quote

“They say you cannot trust a memory that you cannot read.”

— I am Switching to OpenHuman..., at 18:55▶ watch at 18:55
Key Quote

“what I think is the real innovation here is they just packaged the most opinionated, most beginner-friendly version of an agent harness that exists today.”

— I am Switching to OpenHuman..., at 23:27▶ watch at 23:27

Cite this

“I am Switching to OpenHuman....” https://www.youtube.com/watch?v=4xDTGazlYHM. Transcript summary by WhipScribe, https://whipscribe.com/transcript-pages/i-am-switching-to-openhuman.html.

Report this page
What is wrong with this page?