Parallel Agents Side by Side — effect skill for AI agent flows

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

Several agent cards work at once in lanes or an orbit, each with its own status, then merge into one result.

What it does

Built on Three Orbiting Cards by HeyGen (HyperFrames), Apache-2.0. The write-up and recipes below are varg's.

Three to five cards with names (Researcher, Writer, Reviewer) and live status chips; lines converge into a final output card.

When: Multi-agent systems, subagents, parallel cloud agents.

Watch out: Do not make every lane busy with motion; one lane leads at a time while others idle-tick.

Timing: Cards in 0.3 s stagger 0.1 s; status ticks every 0.4–0.8 s; merge 0.6 s.

Also called: multi-agent, agent swarm, parallel runs

In HyperFrames

npx hyperframes add three-orbiting-cards
npx hyperframes add state-chip-rail

In Remotion

agents.map((a,i)=> <AgentCard key={i} name={a.name} status={a.timeline.findLast(s=>s.f<=frame)?.label} style={{left:`${12+i*26}%`}}/>)

In CapCut

Split screen into 3 lanes (Templates → split screen), one recording per lane, then cut to the merged result.

Ready-made components

Where this comes from

Use when

Not for

Install

Example output

https://s3.varg.ai/how-to/previews/c8425cff36e8/take-parallel-agents-lanes.mp4 — The Three Orbiting Cards component used as its header comment describes, with demo copy (credit: Rendered by varg · HyperFrames Three Orbiting Cards, https://hyperframes.heygen.com/catalog/components/three-orbiting-cards)

More AI agent flows skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.