Why Parallel Coding Agents Need a Coordination Layer (So I Built Dibs)

Tue, 04 Aug 2026 00:00:00 +0000

Running one AI coding agent is last year’s workflow. My normal setup today is two or three Claude Code sessions working the same repository from separate git worktrees — one refactoring, one writing tests, one chasing a bug. It is a genuine productivity multiplier, with one recurring failure mode:

Agent A is halfway through refactoring src/auth. Agent B decides the quickest fix for its bug also lives in src/auth/token.go. Neither knows about the other. The result is silent overwrites or an unmergeable diff — produced by two tools that were each doing their job correctly.

Weave: I Built a TypeScript-Native Agent Orchestrator (And Why You Might Want One)

Sun, 05 Jul 2026 00:00:00 +0000

After months of building LLM agent pipelines for real projects, I kept hitting the same three walls: my graph state degraded into any soup, wiring MCP servers into agents meant writing the same glue code over and over, and answering “why did this run cost $4?” required either a SaaS observability subscription or grepping JSON logs at 3 a.m.

So I built weave — a small, opinionated framework for multi-agent workflows in TypeScript. It’s MIT licensed, published on npm, and the core is about 600 lines of code. This post is a tour of what it does and why I made the choices I made.

MCP on Farid

Why Parallel Coding Agents Need a Coordination Layer (So I Built Dibs)

Weave: I Built a TypeScript-Native Agent Orchestrator (And Why You Might Want One)