Find a decision from a call, a page you had open, or what you need to follow up on. LokalBot searches meeting transcripts and screen text you choose to save, with links to the source. Free and open source for Mac. Runs locally by default.
Hi Product Hunt — I'm building LokalBot, a free, open-source Mac app for looking up things from your workday.
What did we agree on? Search a meeting, find the decision, and jump to the part of the call where it came up.
Where was that page? Search screen text you chose to save and open the matching moment.
What do I still need to do? Review outstanding actions without rereading every transcript.
Local by default. It records and transcribes meetings without adding a bot. Screen text and screenshots are optional. The built-in models run on your Mac. Models and updates need downloads; remote models need your explicit approval.
You can also dictate, autocomplete, and make a follow-up draft to review.
What Astra helped me ship. I used GPT-6 Astra in Codex to rebuild the Models setup: see which models are ready, download a replacement before switching, and recover with retry, cancel, and undo. It shipped in 0.8.1 with focused tests and hosted macOS UI checks. Astra helped with development; LokalBot's built-in processing stays local.
Free, with no account required. Apple Silicon Macs, macOS 15 or later.
No comment highlights available yet. Please check back later!
About LokalBot on Product Hunt
“Find what you said or saw on your Mac”
LokalBot launched on Product Hunt on September 18th, 2026 and earned 56 upvotes and 1 comments, placing #79 on the daily leaderboard. Find a decision from a call, a page you had open, or what you need to follow up on. LokalBot searches meeting transcripts and screen text you choose to save, with links to the source. Free and open source for Mac. Runs locally by default.
LokalBot was featured in Productivity (661.1k followers), Open Source (68.8k followers), Artificial Intelligence (479k followers), GitHub (41.4k followers) and OpenAI Day (39 followers) on Product Hunt. Together, these topics include over 330.6k products, making this a competitive space to launch in.
Who hunted LokalBot?
LokalBot was hunted by Stevan Bogosavljević. 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 LokalBot stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hi Product Hunt — I'm building LokalBot, a free, open-source Mac app for looking up things from your workday.
What did we agree on? Search a meeting, find the decision, and jump to the part of the call where it came up.
Where was that page? Search screen text you chose to save and open the matching moment.
What do I still need to do? Review outstanding actions without rereading every transcript.
Local by default. It records and transcribes meetings without adding a bot. Screen text and screenshots are optional. The built-in models run on your Mac. Models and updates need downloads; remote models need your explicit approval.
You can also dictate, autocomplete, and make a follow-up draft to review.
What Astra helped me ship. I used GPT-6 Astra in Codex to rebuild the Models setup: see which models are ready, download a replacement before switching, and recover with retry, cancel, and undo. It shipped in 0.8.1 with focused tests and hosted macOS UI checks. Astra helped with development; LokalBot's built-in processing stays local.
Free, with no account required. Apple Silicon Macs, macOS 15 or later.
Download for Mac · Source code · Privacy
What's something from your workday you keep having to look up?