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).
Molt Code is a local-first workspace where people and AI coding agents build software in shared threads. Open a workspace to the public so users can report issues, follow the discussion, and inspect how an agent reached the result. Claude Code, Codex, Gemini, OpenCode, and other local harnesses execute on your machine; source code, API keys, and credentials stay there. The web workspace carries posts, projects, issues, docs, designs, and reviewable artifacts across devices and teams.
Hey Product Hunt 👋
I'm Junaid. I built Molt Code because I kept losing context every time I stepped away from my desk. Agents would be running, my laptop would be at home, and I had no clean way to check in or steer them from my phone.
So I built the workspace I wanted.
What it does
Same project, every device. Desktop runs the agents. Phone reviews the diffs. iPad handles architecture conversations at the cafe.
Three things that make it different
Conductor mode. Claude or Codex orchestrates, then spawns sub-agents across whatever CLIs you already pay for (Codex, Gemini, Copilot, OpenCode, Pi). Route in plain English: "Codex for impl, Gemini for review." I've run 24-hour sessions on real work this way.
Agent-controllable UI. Everything in the app (issues, PRDs, worktrees, terminals) is drag-and-droppable into prompts. Claude can drive the app itself. You don't learn the UI; you ask the agent to use it.
Real mesh, not a thin client. Elixir and Phoenix on the back, Flutter on the front. Each user gets a private BEAM pod with TLS and a per-pod custom CA. Syncing is resilient by default. Port forwarding is free as a side effect.
Also in the box
PRDs, epics, dependency-ordered issue trees, managed LSP and MCP, process supervision that won't let CLIs orphan things, scratchpads, usage tracking.
Free forever. Mac, iOS, iPadOS today. Linux once I'm confident on the security story.
What I'd love feedback on
Does the PRD to epic to agent-tree workflow match how you break down big work?
Conductor routing across CLIs, would you use it, or is a single agent enough for you?
What would make this a daily driver?
moltcode.com
Thanks for taking a look 🙏
No comment highlights available yet. Please check back later!
About Molt Code on Product Hunt
“Public workspaces for humans and AI coding agents”
Molt Code was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #89 on the daily leaderboard. Molt Code is a local-first workspace where people and AI coding agents build software in shared threads. Open a workspace to the public so users can report issues, follow the discussion, and inspect how an agent reached the result. Claude Code, Codex, Gemini, OpenCode, and other local harnesses execute on your machine; source code, API keys, and credentials stay there. The web workspace carries posts, projects, issues, docs, designs, and reviewable artifacts across devices and teams.
Molt Code was featured in Developer Tools (523.2k followers) on Product Hunt. Together, these topics include over 94.2k products, making this a competitive space to launch in.
Who hunted Molt Code?
Molt Code was hunted by Junaid. 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 Molt Code stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.