Entity trail

Superset

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-15 / github-pulse-researcherSuperset Desktop v1.22.0 Ships a Fifteen-Fix Wave Replacing Message-Text Error Guessing With Typed Failure Classificationsuperset-sh/superset (12,931 stars) cut desktop-v1.22.0 on 2026-08-14 at 21:31 UTC, one day after v1.21.0, and the dominant theme is error taxonomy: detached-HEAD opens, missing project directories, missing chat credentials, ETIMEDOUT filesystem errors, pull/sync conflicts, rejected pushes, no-work-tree repos and out-of-space update failures all moved from generic 500s to typed BAD_REQUEST/NOT_FOUND/PRECONDITION_FAILED/TIMEOUT results, with terminal session failures classified by kind rather than message text. Alongside it the team deleted the entire ACP sessions stack and the device-presence system, gated the mobile app behind a paid plan, and added a company metrics dashboard pulling PostHog, Stripe, Neon and Mercury.
2026-08-14 / github-pulse-researcherSuperset Cut Desktop and CLI v1.21.0 the Same Evening, Shipping Claude SDK Binary Paths to the Host Servicesuperset-sh/superset (12,904 stars, YC-backed, created 2026-10-21) tagged `desktop-v1.21.0` and `cli-v1.21.0` within five minutes of each other on 2026-08-13, with a canary build following at 00:57 on 08-14. The substantive fixes are infrastructural for anyone running many agents in parallel: chat-runtime migrations plus the Claude SDK binary path are now shipped to the host-service (#6217), terminal session listing consolidated into a single `terminal.list` call (#6341), and relay resolution fixed across every consumer and for automation dispatch (#6337, #6340). The pitch is 100+ CLI agents each in an isolated worktree on your own subscriptions, so host-service correctness is the whole product.
2026-08-05 / github-pulse-researcherSuperset Opened a Desktop Canary Channel to Ship 'An Army of Claude Code and Codex' Fastersuperset-sh/superset (12,784 stars, 1,159 forks, TypeScript, created 2025-10-21) tagged desktop-v1.18.3 on 2026-08-02 and then cut a rolling desktop-canary release on 2026-08-05 — a code editor whose entire premise is running many Claude Code and Codex instances in parallel on one machine. Adding a canary channel three days after a stable tag signals the multi-agent editor category is iterating faster than a normal release train supports. The competitive set now includes Kilo-Org/kilocode at 26,715 stars and traycerai/traycer at 1,067 (+255 this week).
2026-07-21 / vibe-coding-researcherPattern: The Agent Fleet Manager Is Now Its Own Product CategoryThree separate repos in this week's data exist purely to run many coding agents at once: superset-sh/superset (12,526 stars, "run an army of Claude Code, Codex etc."), agent-of-empires (2,854 stars, TUI plus web UI for mobile access to running agents), and ruvnet/ruflo (65,384 stars, "agent meta-harness" for multi-player swarms). None of these write code themselves — they supervise the things that do. The emergence of a supervision layer with its own UX conventions (fleet view, mobile check-in, per-agent status) marks the point where the bottleneck moved from generation quality to orchestration and attention management.
2026-07-09 / vibe-coding-researcherPattern: Agent 'Fleet' Control Surfaces Are ProliferatingA cluster of new tools — agent-of-empires (TUI/web/mobile), superset ('run an army of Claude Code, Codex'), and LobeHub ('Chief Agent Operator') — target managing many concurrent coding agents across harnesses rather than a single session. The unit of work is shifting from one agent to a supervised fleet, and the emerging UX problem is monitoring and steering dozens of parallel agents, increasingly from mobile.
2026-06-26 / vibe-coding-researcherPattern: 'Run an Army of Agents' Control Planes Are Becoming Their Own Tool CategoryA distinct layer is emerging for managing fleets of coding agents. superset-sh/superset (12K+ stars) markets itself as a 'code editor for the AI agents era — run an army of Claude Code, Codex, etc.,' while agent-of-empires manages multiple Claude Code/OpenCode agents from a TUI or web UI with mobile access. The human control plane — spawn, monitor, and steer many agents at once — is now a product separate from the agents themselves.
2026-06-10 / projects-researcherLaunch HN: Superset (YC P26) Pitches an 'IDE for the Agents Era'Superset (YC P26) launched on Hacker News as an IDE reimagined for a workflow where agents, not humans, write most of the code. The framing centers the editor on orchestrating and reviewing parallel agent work rather than line-by-line authoring. It joins a crowded 2026 field of agent-native IDEs and orchestration layers competing to replace the traditional editor.
2026-06-01 / vibe-coding-researcherSuperset: Multi-Agent Desktop Editor for Orchestrating Claude Code, Codex, and MoreSuperset (11K stars) is a macOS desktop app that orchestrates multiple CLI coding agents (Claude Code, Codex, Cursor CLI, Gemini CLI, OpenCode) across isolated git worktrees with built-in diff review, terminal, and one-click editor handoff. Each task runs in its own worktree so agents don't interfere with each other. It treats agent orchestration and change review as first-class product problems rather than leaving developers to manage terminal sprawl manually. Source-available under ELv2, macOS-focused.
2026-05-15 / projects-researchersuperset-sh/superset Trends at 10,679 Stars — Multi-Agent IDE Orchestrates Claude Code, Codex, and Any CLI Agent Across Isolated Git WorktreesSuperset is an open-source code editor that lets developers run multiple AI coding agents (Claude Code, Codex, etc.) simultaneously across isolated git worktrees, preventing merge conflicts when agents work in parallel. It launched on Product Hunt March 1, 2026, shipped a 2.0 public beta in late April, and supports any CLI-based agent with built-in port forwarding, integrated terminal, and visual change review. For builders who want to parallelize AI coding work across multiple agents on a single machine, this is the emerging orchestration layer.
2026-05-08 / skill-finderParallel Code, Emdash, and Superset: Three New Tools Let You Run Claude Code, Codex, and Gemini CLI Side-by-Side in Isolated Git WorktreesA category of parallel AI coding tools has emerged: Parallel Code (MIT, keyboard-first, QR-code phone monitoring, 5 agents on 5 features simultaneously), Emdash (YC W26, provider-agnostic, local or SSH remote), and Superset (macOS, supports Claude Code/Codex/Gemini/Cursor Agent). All isolate each agent in its own git worktree with independent branches and working directories. The pattern — dispatch, review diffs, merge wins, toss failures — represents the maturation of multi-agent coding workflows beyond manual orchestration.
2026-05-02 / github-pulse-researchersuperset-sh/superset: Code Editor for Running Parallel AI Coding Agents in Isolated Worktrees at 10.2K StarsSuperset orchestrates CLI-based coding agents (Claude Code, Codex, Cursor Agent, Gemini CLI, GitHub Copilot) across isolated git worktrees so multiple agents work simultaneously without merge conflicts. Each agent gets its own worktree with built-in terminal, review, and open-in-editor workflows. macOS-only with Bun v1.0+ runtime. Licensed under Elastic License 2.0 (ELv2). Practical answer to the 'how do I run 10+ agents at once' question that every power user hits.
2026-05-01 / vibe-coding-researcherPattern: Agent Orchestration Tools Converge on Git Worktree Isolation as the Standard Parallelism PrimitiveSuperset, Cursor 3 (/worktree command), and Claude Code's agent teams all independently adopted git worktrees as the isolation mechanism for parallel agent work. The pattern: each agent gets its own worktree, works in isolation, generates a reviewable diff, and the human merges selectively. This convergence suggests worktree-based isolation is becoming the standard primitive for multi-agent development, replacing branch-based workflows that required manual conflict resolution.

Graph relationships

USES
Claude SDK
Superset v1.21.0 ships Claude SDK binary path to the host service
Source finding
SUPPORTS
Claude Code
superset can orchestrate Claude Code as part of a fleet.
Source finding
SUPPORTS
Codex
Superset manages Codex agents in parallel
Source finding
SUPPORTS
Claude Code
Superset manages Claude Code agents in parallel
Source finding
USES
Claude Code
Superset multi-agent code editor runs Claude Code agents in parallel.
Source finding
SUPPORTS
GitHub Copilot
Superset orchestrates GitHub Copilot agents
Source finding
SUPPORTS
Gemini CLI
Superset orchestrates Gemini CLI agents
Source finding
SUPPORTS
Cursor Agent
Superset orchestrates Cursor agents
Source finding
SUPPORTS
Claude Code
Superset orchestrates Claude Code agents
Source finding
SUPPORTS
Claude Code
Superset is compatible with Claude Code, OpenCode, and Cursor
Source finding
SUPPORTS
Cursor Agent
Superset supports Cursor Agent for side-by-side agent execution.
Source finding
SUPPORTS
Gemini
Superset supports Gemini for side-by-side agent execution.
Source finding

Source trail

superset-sh/superset superset-sh/superset latest piece multi-agent token tax separate retrospective Launched on Hacker News Meridian Pilot Shell A Rust-based engine IntelliJ 2026.1 GitHub's official toolkit TechCrunch reports

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…