This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Margent
Read Markdown docs and @Codex to edit them directly
Margent is a lightweight Markdown reader built around Codex collaboration. While reading a doc, you can highlight any passage, leave an annotation, and @Codex to handle that exact task. Codex receives the selected text, nearby document context, and previous replies, so edits stay focused without long back-and-forth chat prompts. You can also enable auto-monitoring to let Codex pick up new annotations as you review.
Hey Product Hunt,
I built Margent because I kept running into the same problem while working with Codex: the work was centered around long Markdown docs, but reviewing and editing those docs inside a chat flow felt awkward.
When AI writes a long PRD, spec, or technical doc, I don’t always want to ask for a broad rewrite. I often want to point at one specific paragraph, leave a note, and ask Codex to fix exactly that part.
Margent is my attempt to make that workflow feel natural:
- read Markdown locally
- lightly edit when needed
- annotate any passage
- @Codex on a specific annotation
- let Codex see the selected text, local document context, and previous replies
- optionally let Codex monitor new annotations automatically
The app is open source and local-first. The current release is early and focused on macOS Apple Silicon + Codex users, so I’d love feedback from people who use AI agents for product docs, specs, code review notes, or other long-form Markdown workflows.
Would love to hear what feels useful, confusing, or missing.
No comment highlights available yet. Please check back later!
About Margent on Product Hunt
“Read Markdown docs and @Codex to edit them directly”
Margent was submitted on Product Hunt and earned 4 upvotes and 1 comments, placing #145 on the daily leaderboard. Margent is a lightweight Markdown reader built around Codex collaboration. While reading a doc, you can highlight any passage, leave an annotation, and @Codex to handle that exact task. Codex receives the selected text, nearby document context, and previous replies, so edits stay focused without long back-and-forth chat prompts. You can also enable auto-monitoring to let Codex pick up new annotations as you review.
Margent was featured in Productivity (653.8k followers), Open Source (68.5k followers), Developer Tools (514k followers) and GitHub (41.3k followers) on Product Hunt. Together, these topics include over 247.1k products, making this a competitive space to launch in.
Who hunted Margent?
Margent was hunted by 邹Barton. 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 Margent stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
邹Barton