Player profile
Open Swarm
An MIT-licensed local mission-control center for launching, monitoring, and coordinating multiple AI agents in parallel.
Profile
Where it fits
Open Swarm is a locally running orchestrator for managing multiple agents in parallel. Its public README describes a mission-control interface for launching, monitoring, and coordinating swarms of coding agents from one screen.
It belongs in Open Orchestrators because it makes the swarm itself the operating surface: visual dashboards, agent cards, approval queues, prompt templates, skills, MCP tools, views, git worktree isolation, diffs, and local session history.
Builder web analytics
Measure projects built with Open Swarm
Open Swarm coordinates parallel local agents. Agent Analytics gives those agents user-facing outcome data after a swarm-built change ships.
Install Agent Analytics on the project surfaces Open Swarm agents change. Agent Analytics measures user behavior after deployment; it is not a replacement for Open Swarm's local session, cost, approval, or diff tracking.
First loop to measure
- an operator uses Open Swarm to launch, monitor, approve, and coordinate several agent sessions
- one or more swarm-built changes ship to a website, docs site, app, onboarding flow, demo, or support surface
- the changed surface reports visits, sources, CTA clicks, signup, activation, retention, funnels, and experiment events to Agent Analytics
- a later Open Swarm agent fetches the outcome data and turns it into the next task, prompt template, or review decision
Copyable prompt
Use Agent Analytics for this project. If event reporting is missing, add the tracker and report events for this project surface, including Open Swarm-built page, traffic source, CTA click, signup, activation event, funnel step, experiment, or approved agent task. Verify events are arriving. Then fetch the last 7 days and compare them with the prior 7 days. Tell me which Open Swarm-built page, traffic source, CTA click, signup, activation event, funnel step, experiment, or approved agent task moved users toward value, where users dropped off, which sources mattered, and what my agent workflow should improve next.