Comparison
Bystep vs Superset
A desktop “agentic development environment” (Electron) that runs any coding-agent CLI — Claude, Codex, Cursor, OpenCode, Gemini and more — in a terminal per git worktree. It uses the subscriptions and API keys you already have and, in its own words, “never proxies model calls”. macOS first; the Linux build is experimental; no Windows yet.
What Superset is
A desktop “agentic development environment” (Electron) that runs any coding-agent CLI — Claude, Codex, Cursor, OpenCode, Gemini and more — in a terminal per git worktree. It uses the subscriptions and API keys you already have and, in its own words, “never proxies model calls”. macOS first; the Linux build is experimental; no Windows yet.
- Pricing
- Free · Pro $20 ($15 on yearly billing) · Enterprise — as listed on superset.sh/pricing when we checked on 10 Sep 2026. Check their page for current numbers.
Competitor facts checked 10 Sep 2026 · Sources: superset.sh/pricing, github.com/superset-sh/superset
Feature matrix
Where the two actually differ
Every Bystep item here is live in the product today — not a roadmap promise. Competitor claims we couldn't verify first-hand are marked “as far as we know.”
| Bystep | Superset | |
|---|---|---|
| PRD generation | Yes | NoStarts from a worktree and a terminal, not from an idea-to-PRD flow |
| Acceptance criteria per task | Yesids like AC-checkout-1, derived from the PRD, editable by hand | NoNo structured acceptance-criteria field per task, as far as we know |
| Verification gate | Yes`task complete` returns 409 without passing evidence or a recorded override | NoNothing requires evidence before a task counts as done |
| Evidence panel | Yestest output, diff stat, files touched, optional screenshot — stored, not just claimed | No |
| Works with any coding agent | YesClaude Code, Cursor, Codex, Copilot, OpenCode, Gemini CLI via CLI + MCP | YesIts defining trait: Claude, Codex, Cursor, OpenCode, Gemini, Kimi, Grok, Hermes and more |
| Import / export formats | YesSpec Kit, OpenSpec, Backlog.md, Task Master, Kiro, Claude Code Tasks, GitHub Issues, Linear | NoLinear and Slack integrations, not a spec/task format hub |
| Client mode / proposal | Yesclient-viewer share page + proposal for the Studio tier | No |
| Cost per feature | Yesper feature, not just per session | NoNot shown per feature, as far as we know |
| Indonesian language & payments | Yesen/id UI, IDR pricing, QRIS/VA | NoEnglish product, USD pricing |
| Open-source CLI | Yes`@bystep/cli` + `@bystep/mcp`, MIT | PartialSource-available under the Elastic License 2.0 — readable, but not OSI open source |
Honest answer
When to choose Superset instead
- You are a developer who wants one desktop app to drive many different agent CLIs side by side, each in its own terminal and worktree.
- You need remote access, Linear/Slack integrations and a vendor with SOC 2, and you want to be able to read the source.
- Your tasks are engineering work you verify yourself — you don’t need a PRD, a verification gate, or a page to show a non-technical stakeholder.
Keep your agents, add the proof
Bystep runs the agents you already use from one plan, then requires evidence before a task counts as done. The result is readable by people who don’t read diffs.