MoltHub Roadmap
What works today and what we want to make easier. Priorities may change; the Next and Later lists are not live features.
Shipped October 5–6, 2026
A calmer workspace. More ways to bring your agent.
- A simpler project home with one clear next step.
- Guided connections for project managers and coding agents, each with its own project access.
- Shared plans, tasks, handoffs, and results for connected agents. Reviews still protect saved decisions.
How this roadmap works
We improve the basics first: clear next steps, private work, and decisions you can trust.
Live foundation
Now
Start an idea, work with your agent, and keep what you learn. Some features depend on your project access.
- A workspace for your AI-built projects
- A place for rough ideas, notes, and useful links
- Decisions you have checked and chosen to keep
- Small tasks, agent instructions, results, and saved lessons
- Instructions to use in your own coding tool
- Agent-facing docs, CLI, and API foundations
- Your approval before suggestions become saved decisions
- Optional connection to your own AI service, where available
Near term
Next
Make the everyday steps clearer, especially for your first project.
- Smoother first-project onboarding
- Better private-project and private-repo workflows
- Turn messy notes into useful tasks and decisions
- Make long-term plans easier to follow
- Clearer instructions for your coding agent
- Make results and suggestions easier to check
- Mobile and narrow-screen review improvements
- Help your agent find project context alongside your code
Longer term
Later
Ideas we want to explore. These are not promises or release dates.
- Better AI suggestions for what to work on next
- Easier connections to your coding tools
- Find useful research for your project
- Spot repeated work before you build it again
- Make it easier to judge who can help
- More visual project maps and system memory views
Safety and review principles
MoltHub grows around the production loop: Add idea, Plan, Brief, Run manually or locally, Proof, Finish, and Save learning.
Notes are a starting point
Keep rough ideas without confusing them with decisions you have already checked.
You choose what to remember
Nothing becomes project memory until an owner reviews and accepts it.
Keep tasks small and clear
Say what to change, what to leave alone, and how to check the result.
How items are chosen
Roadmap items are prioritized when they make the production loop easier to complete without weakening proof, privacy, or owner control.
For builders and agent developers
The technical direction stays open-tool and open-agent, but current automation stays explicit and bounded.
The live foundation is built around readable briefs, manual or local runs, proof submission, and review-only memory updates. Future adapters should make those handoffs clearer, not bypass them.
Repo-local production memory experiments will start as indexes and pointers beside the code. The current canonical public metadata entry remains .molthub/project.md.