Compare
How Treq's Stacking ADE differs from other agent tools and stacked PR platforms.
Treq is a desktop Stacking Agent Development Environment (ADE). Agents write code fast. Managing the output is the hard part.
Each coding agent gets an isolated workspace. Dependent workspaces form a stack. You review diffs like a pull request, send comments back to the agent, and Treq rebases higher layers when a lower layer moves. Conflicts go to the agent instead of sitting in a merge tool.
The four problems Treq is built around:
| Problem | What Treq does |
|---|---|
| Parallel agents overwrite each other | Isolated workspaces with separate working copies |
| Branches go stale while you iterate | Auto-rebase of dependent workspaces in the background |
| Conflict resolution is grunt work | Auto-resolve: send the conflict to the agent with instructions |
| Large features need smaller, synced PRs | Stacked workspaces that stay on the same rebase chain |
Most agent tools solve the first row. Isolation via git worktrees is now common. Treq's claim is the other three rows: review that feeds the next agent turn, automatic rebase, and a stack that stays current. Git worktrees cannot rebase dependents the way Treq's colocated Jujutsu workspaces do.
Treq also positions itself as an open-source Graphite alternative. Graphite stacks pull requests after you push. Treq stacks local agent workspaces before a pull request exists. Review data stays on your machine by default.
Supported agents today are Claude, Codex, and Cursor. The desktop app is marketed for macOS. The app is Apache 2.0. Pricing keeps the desktop free. Pro adds GitHub integration for private repos and a Treq-managed merge queue. Those cloud features are listed as coming soon.
| Comparison | Best when you care about |
|---|---|
| Treq vs Superset | Broad agent control, team packaging, and review-focused workflows |
| Treq vs Conductor | Mac-native agent workspaces versus stacked review and rebase |
| Treq vs Emdash | Cross-platform open-source breadth versus review and stack depth |
| Treq vs Claude Squad | Terminal tools versus a review-first desktop workspace |
| Treq vs Graphite for AI teams | Stacked PR tooling when agents write most of the code |
| Treq vs Orca | Full IDE-like surface versus branch hygiene and review quality |
New to the category? Start with agent orchestration, git worktrees, and stacked PRs.