32dots HEIDELBERG AI
Curriculum › opencode course › opencode-03
Session 3 medium

Run several agents at once

LESSONLesson 3 · ~20 min

🎯Goal. Split a big job across multiple agents working the same project in parallel, so independent subtasks finish at the same time.

▶ Try this prompt

Session A: write unit tests for the parsing module. Session B: update the README and fix the broken links.

Start two separate opencode sessions on the same project and give each its own focused subtask.

  1. 1opencode supports multi-session parallelism: run multiple agents at once on the same project, each handling a different subtask.
  2. 2Give each session a narrow, independent job — tests in one, docs in another — so they don't collide on the same files.
  3. 3opencode also loads LSP (language server) support automatically, so each agent gets language-server-grade code understanding and navigation while it works.

✓You'll see. Two agents progressing on separate parts of the same project simultaneously, each with full code understanding.

💳Cost. Each running session consumes your model's tokens independently — two agents cost roughly twice one, so parallelise jobs that are genuinely independent.

💡Takeaway. opencode scales sideways: fan independent subtasks out to parallel agents instead of waiting on one.