DeconBear

Hadamard — Development skill for Claude Code

Development community

Hadamard is an independent, experimental agent for practical multi-tool, multi-session, and bridge-assisted agent workflows, learned from the outstanding and valuable experience of Claude code, codex.

How to install Hadamard

This entry records only its repository, not the path inside it, so there is no exact command to give. Open DeconBear/hadamard and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Hadamard does

Hadamard is an independent, experimental agent for practical multi-tool, multi-session, and bridge-assisted agent workflows, learned from the outstanding and valuable experience of Claude code, codex and deepagents.

Alternatives in Development

  • Zeroshot — Runs coding agents as a graph: one agent implements, independent agents review, failures go to repair, and not 1.9k ★
  • Claude Code Skill — Persistent multi-engine coding session manager 326 ★
  • Premiere Pro MCP — Adobe Premiere Pro MCP — independent, local-first server for supported workflows 292 ★

README

Hadamard: Agents as an Engineering Team

[![CI](https://github.com/DeconBear/hadamard/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/DeconBear/hadamard/actions/workflows/ci.yml) [![Publish npm Package](https://github.com/DeconBear/hadamard/actions/workflows/publish-npm.yml/badge.svg?branch=main)](https://github.com/DeconBear/hadamard/actions/workflows/publish-npm.yml) [![npm version](https://img.shields.io/npm/v/actoviq-agent-sdk)](https://www.npmjs.com/package/actoviq-agent-sdk) [![Docs](https://img.shields.io/badge/docs-github%20pages-0f766e)](https://deconbear.github.io/hadamard/)

[English](./README.md) | [Chinese](./README-zh.md)

LLM harnesses are powerful but hard to manage on real engineering and research work — shipping software, running AI-for-Science (AI4S) pipelines, training neural networks and steering experiments. Contexts overflow, tool calls sprawl, runs drift from the plan, and a single agent loop never gets a second opinion.

**Hadamard** exists to make agent engineering and research controllable. Multiple agents on different providers talk to each other — investigating, reviewing, and dispatching in parallel — so problems get considered more thoroughly. One TypeScript runtime provides tools, skills, durable sessions, memory, and MCP, plus a bridge that manages installed agent CLIs (Claude Code, Codex, Cursor, Pi, CodeWhale, Reasonix, Crush) as child processes; the same runtime ships with a terminal UI and a desktop GUI.

Inspired by Claude Code, Codex, Deepagents, and the broader agent ecosystem. Hadamard remains independent with its own public API and documentation.

Hadamard desktop GUI — projects overview Hadamard desktop GUI — chat with a model