Event Horizon is a VS Code extension that visualizes AI coding agents as a living cosmic system. Instead of viewing logs, terminals, or raw agent output, developers observe agent behavior in real time through an interactive universe.
# Event Horizon [](https://marketplace.visualstudio.com/items?itemName=HeytalePazguato.event-horizon-vscode) [](https://open-vsx.org/extension/HeytalePazguato/event-horizon-vscode) [](https://open-vsx.org/extension/HeytalePazguato/event-horizon-vscode) [](https://github.com/HeytalePazguato/event-horizon) **The multi-agent orchestration framework for AI coding.** Tell one agent to build a feature. It creates the plan, spawns the team, assigns roles, tracks budget, and manages the entire project. Works with Claude Code, OpenCode, Cursor, and Cursor.  --- ## The Problem You open three terminals. Claude Code is building the API. OpenCode is writing tests. Cursor is updating the docs. They're all editing the same project. Then Cursor overwrites OpenCode's changes to `server.ts`. OpenCode doesn't know. The build breaks. You spend 20 minutes untangling the mess. **Event Horizon prevents this entirely.** --- ## How It Works ### 1. Create a plan ``` /eh:create-plan Build a REST API with auth, database layer, and tests ``` Event Horizon generates a plan with parallel tracks, dependency annotations, and verify steps. The agent that creates the plan automatically becomes the **orchestrator**. ### 2. The orchestrator spawns the team The orchestrator spawns workers in visible VS Code terminals. Each worker gets a role, a task assignment, and access to the shared knowledge base. ``` Orchestrator → spawns Claude Code (implementer) → claims database tasks Orchestrator → spawns OpenCode (tester)
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.