Marknote — inbox for your AI agents
You run agents from your phone. Now read them there.
Marknote — inbox for your AI agents launched on June 17, 2026 with 3 votes, #6,658 of 22,647 launches that month and more than 50% of that year's launches.
What it does
You can already start your AI agents from your phone — OpenClaw, Hermes, Claude Code, Codex. But what they hand back stays stranded: a terminal you closed, an IDE you'd have to open. You can launch the work from your pocket, but not read it. Marknote closes the loop your agents' output lands in a clean inbox you read on your phone. Markdown rendered, HTML live, nothing to deploy. Edit a line, share any of it with one link. Free to start, first 14 days full
Marknote is the inbox for the documents your agents ship — briefs, code reviews, research, and dashboards in markdown or HTML, hosted the second they're written. Read, edit, and share from your phone. No IDE, no deploy.
Briefs, code reviews, research, dashboards — markdown and HTML, hosted the second your agent writes them. Read it, edit it, share it from your phone. No IDE. No deploy. Five things landed overnight — a morning brief, two code reviews, a competitor teardown, a live dashboard. You skim all of it in one thread, phone in hand, coffee not even poured. Your agent built it as HTML — and it’s a real page at its own link, no deploy. You read it on the phone and drop the link in chat; they open it before you’ve put the cup down. A number in the brief looks off. You fix it right where you’re reading and reply to the agent: “run it again with the real figure.” It picks the work back up — you didn’t.…from marknote.io
Does a similar job
all alternatives →
PlannotatorApr 2026 · github.com · ▲97I started this in January as a hook for Claude Code's plan mode: when it finished planning, instead of approving a wall of text in the terminal, the plan opens in your browser and you could mark it up like a document. Your annotations go back into the agent session. It grew from there. There's now PR-style code review (git, jj, p4, GitHub/GitLab PRs) and annotation for markdown, URLs, and folders. Agents produce a lot of HTML now, so Plannotator renders those artifacts and lets you annotate them too. Nine harnesses are supported: Claude Code, Codex, Copilot CLI, Gemini, OpenCode, Kiro,…
Vibe PocketDec 2025 · vibepocket.com · ▲135Run AI agents like Claude Code, Codex, Opencode on mobile
relaydJan 2026 · relayd.dev · ▲101I kept missing when my Codex agents finished, so I built relayd — a mobile dashboard that sends push notifications and lets me continue agents from my phone. Free tier available. Would love feedback.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, June 2026
the whole month →
Fundraisly▲1,537AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
Homebrew 6.0.0▲1,481Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!
Life & fun · Jun 2026 · vorpus.github.io
Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.
Life & fun · Jun 2026 · hackernewstrends.com