Shard – Stop watching one AI agent code for 45 min. Run four at once

Name: Shard – Stop watching one AI agent code for 45 min. Run four at once
Availability: InStock
Author: nihalgunu

by nihalgunu·Mar 16, 2026·2 points·2 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainWizardry

Git worktrees eliminate merge conflicts while running four AI agents simultaneously.

Strengths

•DAG decomposition with exclusive file ownership prevents conflicts by design
•Self-healing test failures reduce manual intervention after agent runs
•Agent-agnostic backend supports Claude Code, Aider, and Cursor CLI

Weaknesses

•Requires Python 3.11+ and Git 2.20+; Windows support unclear from README
•Parallelization speedup depends heavily on task decomposability

Post Description

The biggest bottleneck in AI-assisted coding right now isn't model quality. It's that you give Claude Code or Cursor a complex task and then sit there watching it work for 30-60 minutes. You can't intervene, you can't do anything useful, you just wait.

Shard takes that one big prompt and automatically decomposes it into a DAG of parallel sub-tasks. Each task gets exclusive file ownership so there are zero merge conflicts by design. Then it dispatches multiple agents across git worktrees simultaneously, merges in topological order, and self-heals test failures.

A 45 minute serial task becomes 4 agents running for 12 minutes.

Open source, cross-platform, agent-agnostic (Claude Code, Aider, Cursor).