Bits is a personal agent that runs on your own machine and never sleeps. A small background daemon does the work: routines wake it on a schedule, and tasks keep going when the app is closed. Every step is saved, so a crash just resumes. Memory lives in plain Markdown files you can read and edit. Risky actions pass the Sentinel, a reviewer that only trusts your own words. It answers with live cards and mini-apps, talks by voice, opens with ⌥Space, and works with any model, including local ones.
Hey Product Hunt 👋 I'm Harsh, and I made Bits.
Always-on agents like Meta's Muse, OpenAI's Dots and Grok Bot changed how I think about assistants: they don't wait for you to open a tab, they keep working and remember things. But they all live on someone else's server. I wanted one that runs on my own laptop, keeps its memory in files I can open, and works with any model, including local ones.
So Bits is:
🟣 Always on: a small background daemon. Routines wake it on a schedule, and work keeps going when the app is closed.
💾 Crash-safe: every step of a turn is saved before the next one. If it crashes, it resumes where it stopped, and finished tools never run twice.
🧠 Memory you can read: a profile, a dated fact log, skills and routines, all plain Markdown in ~/.bits.
🛡️ The Sentinel: risky actions go past an independent reviewer that only trusts your own messages, so a sneaky web page can't talk it into anything. It only asks you when it needs to.
🧩 Live answers: cards, tables, checklists and small persistent mini-apps that you, Bits and other agents can all edit.
🎙️ Voice + ⌥Space: talk to it hands-free, or pop it open from anywhere on your Mac.
🔌 Connect apps over MCP (Notion, Linear, GitHub and more). Keys live in an encrypted vault the model never sees.
It's MIT-licensed. Try the demo in your browser (bits.interfacesforhuman.com/demo), then install it, poke at it, and tell me what it should do next. I'm here all day and reading every comment 🙏
Lots of personal agents launching lately, so going open source is a smart way to stand out. What's the first thing I should ask it to be impressed?
Hey Harsh! Congrats, it's definitely a great idea for someone who would like to try personal agents like Muse, but was concerned about data privacy
Whoa! Congrats on launch. Can I run a team of bits?
Also, which local models do you recommend to try out ?
About Bits on Product Hunt
“An open-source personal agent that gets you things done”
Bits launched on Product Hunt on October 22nd, 2026 and earned 78 upvotes and 7 comments, placing #15 on the daily leaderboard. Bits is a personal agent that runs on your own machine and never sleeps. A small background daemon does the work: routines wake it on a schedule, and tasks keep going when the app is closed. Every step is saved, so a crash just resumes. Memory lives in plain Markdown files you can read and edit. Risky actions pass the Sentinel, a reviewer that only trusts your own words. It answers with live cards and mini-apps, talks by voice, opens with ⌥Space, and works with any model, including local ones.
Bits was featured in Productivity (663.6k followers), Open Source (69k followers), Artificial Intelligence (481.7k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 351.3k products, making this a competitive space to launch in.
Who hunted Bits?
Bits was hunted by Harsh Patel. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Bits stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Harsh Patel