Ross ROSS = Recommend OSS · open-source software intelligence for agents

generalaction/emdash

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider. observed · 2026-08-28

github.com/generalaction/emdash · homepage · TypeScript · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

78/100

  • Activity 99
  • Release rhythm 81
  • Longevity 26
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 1.0
  • age_days: 370
  • days_rel: 47
  • days_push: 8
  • n_releases_24m: 121

Full methodology

Adoption not part of the score

5504 stars · 564 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Emdash is an open-source desktop application (Agentic Development Environment) for running multiple AI coding agents in parallel, each isolated in its own Git worktree. It supports 30+ CLI-based agents like Claude Code, Codex, and Amp, with issue tracker integrations, diff review, scheduled automations, and remote development over SSH.

Use cases

  • run multiple AI coding agents in parallel on different tasks
  • isolate agent changes in separate git worktrees and branches
  • send Linear, Jira, or GitHub issues directly to a coding agent
  • review agent diffs and open pull requests from one place
  • schedule recurring agent tasks on a cron schedule
  • run coding agents on remote machines over SSH
  • preview local dev servers in an in-app browser while agents work
  • manage reusable prompts, skills, and MCP servers for agents

When to choose

  • you want to explore multiple fixes or features simultaneously with different agents
  • you use several CLI coding agents (Claude Code, Codex, Amp, etc.) and want one unified workspace
  • you need issue-to-agent workflows with trackers like Linear, Jira, or GitHub
  • you want isolated git worktrees per task to avoid agents interfering with each other
  • you need to run agents on remote machines or provisioned workspaces

When to avoid

  • you only need a single agent session and are happy with a plain terminal
  • you want a fully autonomous CI-style agent pipeline rather than an interactive desktop environment
  • you need a headless or server-only solution without a GUI
  • your workflow does not involve git-based repositories

Facets

application · maturity active

agent-framework developer-tools cli workflow-automation scheduling mcp chat-interface developer-tools artificial-intelligence large-language-models version-control windows cross-platform coding-agents git-worktrees parallel-agents agentic-development-environment claude-code codex issue-tracker-integration remote-development ssh diff-view in-app-browser orchestration ai-agents automation command-line macos linux desktop typescript

10 sources

Member repositories

RepositoryRoleHealth v2
generalaction/emdashmain78

For agents

markdown · JSON · MCP: product_card(name="generalaction/emdash")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem