ModernevsSuperset
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Moderne
Moderne · Agent harness
MCP
Panel
6.11 spec wins
- Reliability
- 6.5
- Usefulness
- 6.3
- Cost
- 4.7
- Longevity
- 6.8
“It lands one change across a hundred thousand repositories, so a bad recipe has an unusually long attendee list.”
Superset
Superset · Agent harness
MCP
Panel
6.43 spec wins
- Reliability
- 6.5
- Usefulness
- 6.2
- Cost
- 6.3
- Longevity
- 6.7
“Superset-arm64.dmg or Superset-x64.dmg: the first orchestration decision is which Mac you bought.”
Spec by spec
| Spec | Moderne | Superset |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | cloud, local | local |
| Platforms | macos, linux, windows, web | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | No |
| MCP server | Yes | Yes |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | YesChanges are expressed as recipes over the Lossless Semantic Tree, so a single reviewed recipe applies across every affected file and repository. | No |
| Git operations | Yes | Yes |
| Browser control | No | Yes |
| Sandboxed execution | No | No |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | undisclosed | via managed agents (Claude Code, Codex, Cursor Agent, GitHub Copilot, Gemini CLI, Kimi Code, Mistral Vibe, OpenCode, Droid, Amp) |
| Bring your own model | No | No |
| Local models | No | No |
| Cost | ||
| Pricing model | seat | seat |
| Starts at | n/a | $15/mo |
| Free tier | No | Yes |
| Bring your own key | No | No |
| Openness | ||
| Open source | No | No |
| License | proprietary | Elastic License 2.0 |
| GitHub stars | n/a | 14,809 |
Which one would each critic pick
| Critic | Moderne | Superset | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.3 | 7.0 | Superset — Pick Superset if you run Claude Code, Codex, Gemini CLI, Copilot or Kimi Code side by side and want a browser next to the diff; pick Orca if you want the same thing under MIT. |
| El Crítico | 5.8 | 6.3 | Superset — Remote access is beta, the mobile app is coming soon, and the tagline promises 100-plus agents in parallel on a host with no sandbox; the ambition outruns the shipped parts. |
| El Profesor | 7.5 | 6.5 | Moderne — Context is a Lossless Semantic Tree, a compiler-accurate representation of the source, so edits are computed over structure instead of inferred from tokens. |
| La Inversora | 7.0 | 7.0 | no preference |
| La Jefa | 6.3 | 6.5 | Superset — SAML SSO, SCIM, audit logs, a SOC 2 Type II report and IP restrictions all sit in an Enterprise tier priced by sales on annual billing; approved with conditions. |
| El Hacker | 3.8 | 5.3 | Superset — Elastic License 2.0, so I can read and build it but not host it for others; a CLI, and no model settings because the agents bring their own. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.