Something shifted when agents arrived. Our work moved back to our machines — markdown files, a terminal, a local codebase.
The filesystem has become the best shared context layer across all your work, making agents more capable and autonomous.
But local was built for one.
But you still need to plan with your team, track what's happening, and review what agents produce. So you're pulled back into Notion, Linear, GitHub — siloed tools that don't see your local environment. Context gets lost in translation.
What happens when you want to run three agents at once? Your filesystem has no native version control. Git wasn't built for this — manual tracking, no parallel local branches, complex merging. Agents deserve better infrastructure.
And now agents can single-shot entire workflows as apps — a custom dashboard, a review tool, a planning canvas. But the hard part isn't generation. It's integration, permissions, collaboration.
Mod is collaborative infrastructure for local agent workflows.
Point it at any folder. That folder becomes a workspace — branchable, queryable, shareable — without leaving your filesystem.
Run parallel agents. Each gets its own branch. They can see each other's work, live, before anything merges. Your teammate can join from their machine and leave a comment on the plan before the first line of code is written.
When the work is done, you review everything in one place. Conflicts surface before they break anything. You merge with full context.
Works with Claude Code, Codex, or any agent you already run. Your setup stays the same. What it can do changes.
Your local environment.
Now built for a team.