oh-my-agent

first-fluke/oh-my-agent is ranked 10,619 among these 8 peers; LiveBench/LiveBench is ranked 10,623.

** A planner breaks the work down, engineers build in parallel, a reviewer checks the result, and a debugger fixes root causes. It also does cited research, slide decks, videos and images. Most steps leave a file you can open, and in the long-running workflows a gate can send the agent back to work until your own , or script passes. Run this from your project root: Then run and type in your agent. Watch the full video (35s) What you

get **Workflows** are what you type (or just say). They call in **roles**, the specialists. **Skills** are the know-how: each role carries its own, and your agent loads the rest whenever a task needs them. Most also start from a plain request (keyword banks in up to 11 languages) | "review this PR" | | **33 skills** | Domain know-how that loads only when a task needs it: UI, APIs, schemas, Terraform, CI, security, git, observability | loads by itself, e. "add a

Terraform S3 bucket" | | **Files you can open** | Plans, design docs, API contracts, ADRs, bug notes, per-agent results, security evidence, HTML explainers, recaps | | | **Checks that don't take the agent's word** | In a long-running workflow, your own , or script must pass before the agent may stop; checks that a run left its plan, QA and refactor files | , then | | **Research and content** | Cited search, market research, papers, slide decks, MP4 videos, images, local voice, PDF/HWP to Markdown | , | | **One folder, 14

runtimes** | One portable directory, written into each runtime's own config files | | **Install** · **First 5 minutes** · **The team** · **Which workflow? ** · **Everything in the box** · **Works with** · **Verification** · **FAQ** · **Docs** Install The script installs bun if it is missing, installs the command globally ( , skipped when is already on your PATH), then starts the interactive setup. The global command matters: the hooks (keyword detection, the Stop gate) and several workflows call , and the hooks silently do nothing when they cannot find it. If

you skip the script, install it yourself with ( or also work). Windows, or without the install script On Windows the installer hides Antigravity, Hermes, and Kimi, and the hook wrapper is a bash script. The default Aside browser MCP installs through , so deselect it if you have no bash. The setup asks for your response language, which agent runtimes to wire up, capability providers, a browser MCP, a model preset, and a skill preset. **Pick for the skill preset if

you are unsure**: workflows are always installed, and several of them ( , , , , , ) need skills that only includes. What the installer also does by default Installs **bun** (required). Tries **uv**, **Serena** ( ), and **CUE** ( or ), and continues with a warning if any of them fails. Pre-selects the **Aside** browser MCP in the interactive setup, and installs it with only if you keep it selected. Deselect it in the browser MCP step, or change it later with . Uses **AgentMemory** for semantic memory, which

runs and registers it as a login service (launchd, systemd user unit, or Windows scheduled task). Asks before linking skills