You're juggling Claude Code, Codex, random OSS models. Configuring workflows. Debugging agents.

We did the work. Tested everything. Kept what actually shipped.

Install OmO. Type ultrawork. Done.

Copy and paste this prompt to your LLM agent (Claude Code, AmpCode, Cursor, etc.):

Install and configure oh-my-matrix by following the instructions here:
https://raw.githubusercontent.com/Y-Square-T3/oh-my-matrix/refs/heads/dev/docs/guide/installation.md

Or read the Installation Guide, but seriously, let an agent do it. Humans fat-finger configs.

Fetch the installation guide and follow it:

curl -s https://raw.githubusercontent.com/Y-Square-T3/oh-my-matrix/refs/heads/dev/docs/guide/installation.md

Note: Use the published package and binary name oh-my-matrix. Inside matrix.json, the compatibility layer now prefers the plugin entry oh-my-matrix, while legacy oh-my-matrix entries still load with a warning. Plugin config files still commonly use oh-my-matrix.json or oh-my-matrix.jsonc, and both legacy and renamed basenames are recognized during the transition.

We're past the era of reading docs. Just paste this into your agent:

Read this and tell me why it's not just another boilerplate: https://raw.githubusercontent.com/Y-Square-T3/oh-my-matrix/refs/heads/dev/README.md

You're actually reading this? Wild.

Install. Type ultrawork (or ulw). Done.

Everything below, every feature, every optimization, you don't need to know it. It just works.

Even only with following subscriptions, ultrawork will work well (this project is not affiliated, this is just personal recommendation):

• ChatGPT Subscription ($20)
• Kimi Code Subscription ($0.99) (*only this month)
• GLM Coding Plan ($10)
• If you are eligible for pay-per-token, using kimi and gemini models won't cost you that much.

Sisyphus (claude-opus-4-6 / kimi-k2.5 / glm-5 ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway.

Hephaestus (gpt-5.4) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. The Legitimate Craftsman.

Prometheus (claude-opus-4-6 / kimi-k2.5 / glm-5 ) is your strategic planner. Interview mode: it questions, identifies scope, and builds a detailed plan before a single line of code is touched.

Every agent is tuned to its model's specific strengths. No manual model-juggling. Learn more →

Anthropic blocked Matrix because of us. That's why Hephaestus is called "The Legitimate Craftsman." The irony is intentional.

We run best on Opus, but Kimi K2.5 + GPT-5.4 already beats vanilla Claude Code. Zero config needed.

When Sisyphus delegates to a subagent, it doesn't pick a model. It picks a category. The category maps automatically to the right model:

Agent says what kind of work. Harness picks the right model. ultrabrain now routes to GPT-5.4 xhigh by default. You touch nothing.

You dialed in your Claude Code setup. Good.

Every hook, command, skill, MCP, plugin works here unchanged. Full compatibility, including plugins.

LSP, AST-Grep, Tmux, MCP actually integrated, not duct-taped together.

• LSP: lsp_rename, lsp_goto_definition, lsp_find_references, lsp_diagnostics. IDE precision for every agent
• AST-Grep: Pattern-aware code search and rewriting across 25 languages
• Tmux: Full interactive terminal. REPLs, debuggers, TUI apps. Your agent stays in session
• MCP: Web search, official docs, GitHub code search. All baked in

MCP servers eat your context budget. We fixed that.

Skills bring their own MCP servers. Spin up on-demand, scoped to task, gone when done. Context window stays clean.

The harness problem is real. Most agent failures aren't the model. It's the edit tool.

"None of these tools give the model a stable, verifiable identifier for the lines it wants to change... They all rely on the model reproducing content it already saw. When it can't - and it often can't - the user blames the model."

- Can Bölük, The Harness Problem

Inspired by oh-my-pi, we implemented Hashline. Every line the agent reads comes back tagged with a content hash:

11#VK| function hello() {
22#XJ|   return "world";
33#MB| }

The agent edits by referencing those tags. If the file changed since the last read, the hash won't match and the edit is rejected before corruption. No whitespace reproduction. No stale-line errors.

Grok Code Fast 1: 6.7% → 68.3% success rate. Just from changing the edit tool.

Run /init-deep. It generates hierarchical AGENTS.md files:

project/
├── AGENTS.md              ← project-wide context
├── src/
│   ├── AGENTS.md          ← src-specific context
│   └── components/
│       └── AGENTS.md      ← component-specific context

Agents auto-read relevant context. Zero manual management.

Complex task? Don't prompt and pray.

/start-work calls Prometheus. Interviews you like a real engineer, identifies scope and ambiguities, builds a verified plan before touching code. Agent knows what it's building before it starts.

Skills aren't just prompts. Each brings:

• Domain-tuned system instructions
• Embedded MCP servers, on-demand
• Scoped permissions. Agents stay in bounds

Built-ins: playwright (browser automation), git-master (atomic commits, rebase surgery), frontend-ui-ux ( design-first UI).

Add your own: .matrix/skills/*/SKILL.md or ~/.config/matrix/skills/*/SKILL.md.

Want the full feature breakdown? See the Features Documentation for agents, hooks, tools, MCPs, and everything else in detail.

New to oh-my-matrix? Read the Overview to understand what you have, or check the * *Orchestration Guide** for how agents collaborate.

To remove oh-my-matrix:

1. Remove the plugin from your Matrix config

   Edit ~/.config/matrix/matrix.json (or matrix.jsonc) and remove either "oh-my-matrix" or the legacy "oh-my-matrix" entry from the plugin array:

   # Using jq
   jq '.plugin = [.plugin[] | select(. != "oh-my-matrix" and . != "oh-my-matrix")]' \
       ~/.config/matrix/matrix.json > /tmp/oc.json && \
       mv /tmp/oc.json ~/.config/matrix/matrix.json

2. Remove configuration files (optional)

   # Remove plugin config files recognized during the compatibility window
   rm -f ~/.config/matrix/oh-my-matrix.jsonc ~/.config/matrix/oh-my-matrix.json \
         ~/.config/matrix/oh-my-matrix.jsonc ~/.config/matrix/oh-my-matrix.json
   
   # Remove project config (if exists)
   rm -f .matrix/oh-my-matrix.jsonc .matrix/oh-my-matrix.json \
         .matrix/oh-my-matrix.jsonc .matrix/oh-my-matrix.json

3. Verify removal

   matrix --version
   # Plugin should no longer be loaded

Features you'll think should've always existed. Once you use them, you can't go back.

See full Features Documentation.

Quick Overview:

• Agents: Sisyphus (the main agent), Prometheus (planner), Oracle (architecture/debugging), Librarian (docs/code search), Explore (fast codebase grep), Multimodal Looker
• Background Agents: Run multiple agents in parallel like a real dev team
• LSP & AST Tools: Refactoring, rename, diagnostics, AST-aware code search
• Hash-anchored Edit Tool: LINE#ID references validate content before applying every change. Surgical edits, zero stale-line errors
• Context Injection: Auto-inject AGENTS.md, README.md, conditional rules
• Claude Code Compatibility: Full hook system, commands, skills, agents, MCPs
• Built-in MCPs: websearch (Exa), context7 (docs), grep_app (GitHub search)
• Session Tools: List, read, search, and analyze session history
• Productivity Features: Ralph Loop, Todo Enforcer, Comment Checker, Think Mode, and more
• Doctor Command: Built-in diagnostics (bunx @matrix-ai/oh-my-matrix doctor) verify plugin registration, config, models, and environment
• Model Fallbacks: fallback_models can mix plain model strings with per-fallback object settings in the same array
• File Prompts: Load prompts from files with file:// support in agent configurations
• Session Recovery: Automatic recovery from session errors, context window limits, and API failures
• Model Setup: Agent-model matching is built into the Installation Guide

Opinionated defaults, adjustable if you insist.

See Configuration Documentation.

Quick Overview:

• Config Locations: The compatibility layer recognizes both oh-my-matrix.json[c] and legacy oh-my-matrix.json[c] plugin config files. Existing installs still commonly use the legacy basename.
• JSONC Support: Comments and trailing commas supported
• Agents: Override models, temperatures, prompts, and permissions for any agent
• Built-in Skills: playwright (browser automation), git-master (atomic commits)
• Sisyphus Agent: Main orchestrator with Prometheus (Planner) and Metis (Plan Consultant)
• Background Tasks: Configure concurrency limits per provider/model
• Categories: Domain-specific task delegation (visual, business-logic, custom)
• Hooks: 25+ built-in hooks, all configurable via disabled_hooks
• MCPs: Built-in websearch (Exa), context7 (docs), grep_app (GitHub search)
• LSP: Full LSP support with refactoring tools
• Experimental: Aggressive truncation, auto-resume, and more

Want the philosophy? Read the Ultrawork Manifesto.

I burned through $24K in LLM tokens on personal projects. Tried every tool. Configured everything to death. Matrix won.

Every problem I hit, the fix is baked into this plugin. Install and go.

If Matrix is Debian/Arch, OmO is Ubuntu/Omarchy.

Heavy influence from AmpCode and Claude Code. Features ported, often improved. Still building. It's OpenCode.

Other harnesses promise multi-model orchestration. We ship it. Stability too. And features that actually work.

I'm this project's most obsessive user:

• Which model has the sharpest logic?
• Who's the debugging god?
• Who writes the best prose?
• Who dominates frontend?
• Who owns backend?
• What's fastest for daily driving?
• What are competitors shipping?

This plugin is the distillation. Take the best. Got improvements? PRs welcome.

Stop agonizing over harness choices. I'll research, steal the best, and ship it here.

Sounds arrogant? Have a better way? Contribute. You're welcome.

No affiliation with any project/model mentioned. Just personal experimentation.

99% of this project was built with Matrix. I don't really know TypeScript. But I personally reviewed and largely rewrote this doc.

• Indent
  • Making Spray - influencer marketing solution, vovushop - crossborder commerce platform, vreview - ai commerce review marketing solution
• Google
• Microsoft
• ELESTYLE
  • Making elepay - multi-mobile payment gateway, OneQR - mobile application SaaS for cashless solutions

Special thanks to @junhoyeo for this amazing hero image.