Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Superset

Terminal to run 10 parallel coding agents

Details

External ID
46368739
Source
HN
Company
—
Product
Superset - the open source IDE for the AI Agents era
Website domain
superset.sh
Launched
Dec. 23, 2025
Cohort
—
Upvotes
96
Upvotes percentile
0.8969465648854962
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

Hey HN, we’re Avi, Kiet, and Satya. We’re building Superset, an open-source terminal made for managing a bunch of coding agents (Claude Code, Codex, etc) in parallel.- Superset makes it easy to spin up git worktrees and automatically setup your environment- Agents and terminal tabs are isolated to worktrees, preventing conflicts- Built-in hooks [0] to notify when your coding agents are done/needs attention,- A diff viewer to review the changes and make PRs quicklyWe’re three engineers who’ve built and maintained large codebases, and kept wanting to work on as many features in parallel as possible. Git worktrees [1] have been a useful solution for this task but they’re annoying to spin up and manage. We started superset as a tool that uses the best practices we’ve discovered running parallel agents.Here is a demo video:https://www.youtube.com/watch?v=pHJhKFX2S-4We all use Superset to build Superset, and it more than doubles our productivity (you’ll be able to tell from the autoupdates). We have many friends using it over their IDE of choice or replacing their terminals with Superset, and it seems to stick because they can keep using whatever CLI agent or tool they want while Superset just augments their existing set of tools.Superset is written predominantly in Typescript and based on Electron, xterm.js, and node-pty. We chose xterm+node-pty because it's a proven way to run real PTYs in a desktop app (used by VSCode and Hyper), and Electron lets us ship fast. Next, we’re exploring features like running worktrees in cloud VMs to offload local resources, context sharing between agents, and a top-level orchestration agent for managing many worktrees or projects at once.We’ve learned a lot building this: making a good terminal is more complex than you’d think, and terminal and git defaults aren’t universal (svn vs git, weird shell setups, complex monorepos, etc.).Building a product for yourself is way faster and quite fun. It's early days, but we’d love you to try Superset across all your CLI tools and environments, we welcome your feedback! :)[0] https://code.claude.com/docs/en/hooks[1] https://git-scm.com/docs/git-worktree

Enrichment

Theme
developer tools for AI agents
Vertical
Horizontal
Function
Agent / copilot
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
terminal for running parallel coding agents
Manually corrected
False

Could you build this?

Partial A basic UI managing terminal tabs and invoking git worktrees can be vibe-coded, but robust process supervision and pseudo-terminal (PTY) virtualization across multiple concurrent AI agents is complex.

What it would actually take: The software is typically an Electron or Tauri desktop application integrating Rust/C++ node-pty bindings and libgit2. The hard parts involve reliable multi-pty concurrency management, stream multiplexing, clean background process lifecycle control, and automated shell environment sandbox isolation across diverse agent workloads. This demands solid systems-level desktop tooling and Unix process management engineering.

Discussion

20 comments analyzed.

Competitors mentioned: Cursor agents, Claude Code (CLI agent), Catnip (GitHub workspaces-based), Devin, CC, Codex, Gemini-cli

Concerns raised: Cost-benefit unclear: 10x the cost with nothing to show, Limited use cases: need for parallelization overhead vs actual value, Requires clear, non-overlapping tasks to be effective, Git worktrees approach has limitations with conflicts and merges, Better suited only for CLI-agent-first workflows, not everyone

Feature requests: Support SSHing into arbitrary/existing VMs (local and cloud), Integration with project planning tools (Circleback notes → tickets), Custom playbooks for task selection before parallelization, Improved Git merge/conflict UX for parallel agent workflows

Competitors

Other products that read as similar to this one — 162 launches clear the similarity bar, closest 8 shown.

Attention rank: #26 of 163 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 36 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.