Treq vs Superset
Two local-first ADEs for different workflows: stacked changes or broad agent control.
Treq and Superset both run coding agents in isolated workspaces and give you a place to review the result. They sit in the same product category. The workflow changes after the agents start writing code.
Treq is built around human review, stacked workspaces, auto-rebase, and sending conflicts back to the agent. Superset is built around running many CLI agents in parallel. It also sells paid plans for teams.
At a Glance
| Treq | Superset | |
|---|---|---|
| Positioning | Stacking ADE, open-source Graphite alternative | Code editor for AI agents, software-factory platform |
| Isolation model | Jujutsu workspaces over a colocated Git repo | Git worktrees per task |
| Review surface | PR-style diffs, line comments sent back to the agent | Diff and file review inside the app |
| Stacked changes | Core workflow | Not emphasized publicly |
| Auto-rebase | Core workflow | Not emphasized publicly |
| Conflict handling | Send resolution instructions to the agent | Manual, unless you drive it yourself |
| Provider model | Claude, Codex, and Cursor shown today | Very broad CLI agent support |
| Remote or cloud workspaces | Roadmap: SSH remote development | Remote workspaces and enterprise packaging |
| License | Apache 2.0 | Source-available under ELv2 |
| Pricing | Free desktop, Pro coming for GitHub and merge queue | Free tier, Pro, and Enterprise |
What Each Product Does
Treq is a desktop Stacking ADE. Each agent gets an isolated workspace with its own working copy, terminal, and line of history. You arrange dependent workspaces into a stack, review each layer, and send comments back to the agent. When a lower layer moves, Treq rebases the workspaces above it. If a rebase hits a conflict, you send it to the agent instead of resolving it by hand.
Superset is a local-first desktop workspace for many coding agents. It launches CLI agents in isolated Git worktrees and adds chat, browser, review, and automation tools. Its public materials focus on parallel scale, integrations with GitHub, Linear, and Slack, plus paid plans for teams.
Both products solve the same first problem. Several agents should not share one checkout, so each task gets its own directory. See agent orchestration for why that isolation is required.
Feature Comparison
| Feature | Treq | Superset |
|---|---|---|
| Local-first desktop app | Yes | Yes |
| Parallel agent sessions | Yes | Yes, with an explicit 100+ agent ambition |
| Workspace isolation | Yes | Yes |
| Review and diff UI | PR-style diffs with line comments | Yes |
| Comments sent back to the agent | Yes | Review surfaces exist, agent-loop feedback is not the center of the public pitch |
| Stacked PR or stacked workspace support | Yes | Not emphasized publicly |
| Auto-rebase of dependents | Yes | Not emphasized publicly |
| Agent-driven conflict resolution | Yes | Not emphasized publicly |
| Automations and scheduling | Not public on the site today | Yes |
| Remote or cloud workspaces | Planned, not shipped | Yes |
| Open source | Apache 2.0 | Source-available under ELv2 |
Where They Differ
Both products run parallel agents in isolated workspaces. Git worktrees give Superset isolation. They do not give it Treq's automatic rebase of a dependent stack. Treq uses colocated Jujutsu workspaces so a target move can rebase every layer above it in the background.
Treq organizes agent work as linked, reviewable layers. A large feature should ship as smaller PRs that stay in sync. Diff comments return to the agent. Auto-rebase keeps the stack current. Conflicts stay in the review loop instead of becoming a separate merge chore.
Superset focuses on breadth. Its public materials feature provider coverage, automations, remote workspaces, and team plans. This model fits teams that want one control plane for many agents, including agents Treq does not list today.
Running many agents is becoming a standard feature. Treq's distinction is the stack that connects their work. That workflow must track each dependency, review layer, and rebase.
Pricing and Licensing
Treq's desktop app is free and open source under Apache 2.0. Pricing lists Free for public GitHub repos and Pro at $15 per user per month. GitHub integration and the merge queue are marked coming soon on that page. Local review stays on your machine either way.
Superset offers a free tier, Pro pricing around $15 per user per month when billed yearly, and custom Enterprise pricing. Its desktop code is source-available under Elastic License 2.0, which is not the same as Apache-style open source.
In both cases you still pay the underlying model providers for Claude, Codex, or any other agent usage.
Who Should Choose Which
Choose Treq if you:
- Care more about reviewing and shipping AI-generated code than about launching the largest number of agents.
- Want stacked workspaces, automatic rebasing, and agent-driven conflict resolution as the default workflow.
- Prefer Apache 2.0 and a local-only review loop until you opt into GitHub features.
- Are looking for a Graphite-like stacked workflow built for coding agents.
Choose Superset if you:
- Need broad CLI agent support and frequent provider switching.
- Want remote workspaces, automations, and team or enterprise packaging today.
- Prefer a product that already has self-serve team plans and compare content.
- Care more about orchestration breadth than stacked PR discipline.
Next Steps
- Treq vs Conductor: Mac-native agent workspaces versus stacked review workflows.
- Treq vs Graphite for AI teams: why stacked PR tooling matters once agents write most of the code.
- Human-in-the-loop review workflow: how review comments become the next agent prompt.
- Stacked PR workflow: how dependent branches stay reviewable.
- Installation: install Treq and open a repository.