Product Thumbnail

Omi CLI

AI coding agents that work while you're away.

Software Engineering
Developer Tools
Artificial Intelligence
Visit WebsiteSee on Product HuntTwitter ⧉Npm ⧉YouTube ⧉

Hunted byOm Prakash SahooOm Prakash Sahoo

Omi can build anything. Give Omi a coding task and let it get to work: it reads your repo, fixes bugs, runs tests, and uses a real browser to check your app. Parallel subagents tackle tasks in separate worktrees. Background agents keep going after you close the terminal; cloud agents can open PRs. Review changes as diffs, undo mistakes, and choose from 13 models or bring your own. Free to start: npm i -g @builditomi/cli

Top comment

Hey Product Hunt! I'm Om, the maker of BuildItOmi.

Our idea has always been simple: Omi can build anything. Omi CLI brings that to your terminal.

What it does:

  • Reads your repo, makes a plan, and shows every edit as a diff you approve (yes / no / always)

  • Runs your tests and keeps going until they pass

  • Auto picks the model for each turn from 13 models (DeepSeek, Gemini, Gemma, gpt-oss, GLM), so everyday edits stay cheap and hard problems get a stronger model

  • /undo puts back every file the last task changed, even without git

  • One plan in USD with clear 5-hour and weekly limits, and a Free plan to try it

New in 0.5.0 (out today on npm):

  • Subagents that edit in parallel, each in its own git worktree, merged back three-way

  • Built-in browser testing: Omi opens your app in headless Chrome, clicks through it and reports console errors and failed requests

  • Background agents (omi bg "task") that keep working after you close the terminal

  • Cloud agents (omi cloud "task") that run on your repo's GitHub Actions and open a pull request

Honest numbers: on our first public benchmark (10 small tasks, judged by hidden tests the agent never saw) Omi CLI solved 10 out of 10. It is a small sample, and the full runs are on cli.builditomi.com/benchmark.

Try it: npm i -g @builditomi/cli, then run omi in any project.

I would love your feedback: which task should Omi CLI get better at next?

Comment highlights

The parallel subagents in separate worktrees caught my eye — I run coding agents on real repos and the merge is usually where things get messy. When two subagents touch the same file, does the three-way merge pause for you to resolve it, or does it pick a winner and tell you after? Curious how that plays out on a bigger refactor where overlap is almost guaranteed.

congrats on the launch om. diff before every edit is the part i care most, i dont let any agent write without it. to your question, i would want it better at explaining why auto picked this model for the task. when the result is bad i never know if its the model or my prompt. could the diff show which model made it?

13 models in one terminal agent is handy. Can I set a cheaper model for small edits and switch to a bigger one for refactors, or is it a manual switch each time?

once /test allows npm test for the session, what happens if it later edits the test script in package.json?

About Omi CLI on Product Hunt

“AI coding agents that work while you're away.”

Omi CLI launched on Product Hunt on November 22nd, 2026 and earned 90 upvotes and 11 comments, placing #8 on the daily leaderboard. Omi can build anything. Give Omi a coding task and let it get to work: it reads your repo, fixes bugs, runs tests, and uses a real browser to check your app. Parallel subagents tackle tasks in separate worktrees. Background agents keep going after you close the terminal; cloud agents can open PRs. Review changes as diffs, undo mistakes, and choose from 13 models or bring your own. Free to start: npm i -g @builditomi/cli

Omi CLI was featured in Software Engineering (43.3k followers), Developer Tools (523.5k followers) and Artificial Intelligence (484.3k followers) on Product Hunt. Together, these topics include over 243.9k products, making this a competitive space to launch in.

Who hunted Omi CLI?

Omi CLI was hunted by Om Prakash Sahoo. 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 Omi CLI stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.