Run parallel local coding agent sessions
A developer runs up to 10 coding agent sessions at once, using Claude Code and local models on RTX 3090s with cached contexts for daily development work.
Done withClaude Code
- What they did
- Roark66 runs coding agents on RTX 3090s with 24GB each, using Claude Code alongside local models. They keep up to 10 agent sessions open at once, though never more than 5 are active at the same moment. Because they control inference, they keep full contexts cached in RAM and can save the cache to disk, so a session isn't re-read in full after sitting idle.
- How it went
- Holding about 15 full contexts cached in RAM pushes their local cache utilisation to 95% or more. They say their usage of roughly 1.3B input tokens a week would cost thousands of USD at API prices.
- Worth knowing
- Cloud caches expire after 5 minutes or 1 hour, so an idle 500k context gets billed as full input again; local caching avoids that, but you need enough RAM to hold the contexts.
Try it yourself with Claude Code
I want to work on [N] separate tasks in my repo at [path] at the same time. For each task, create its own git worktree and branch, work on it independently, run the tests, and summarize what changed. The tasks are: [task 1], [task 2], [task 3]. Stop when each branch has a passing diff ready for my review, and do not merge anything.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: HN · Oct 7, 2026
Related use cases
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Build Godot games with paired design and coding agents
Cowork handles design docs, task queues and playtests while Claude Code writes GDScript and runs Godot and git.
Find and clean leads for recruiting outreach
A recruiting agency owner uses Claude to find leads; a commenter uses it to clean messy data and draft personalized outreach that gets replies.
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Build an iCloud skill with a Muse agent
A screen-reader user asked their Muse agent to build an iCloud skill and it produced something, but accessibility problems with the text field and conversation navigation got in the way.
Build a first real project with Replit Agent
A student completed a real build with Replit Agent, spending about $65 in agent usage and finding the cost unexpected.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.