{"repo":"Keyoku-ai/keyoku","free":true,"listed":false,"github":"https://github.com/Keyoku-ai/keyoku","clone":"git clone https://github.com/Keyoku-ai/keyoku.git","description":"The harness with muscle memory — activity tracing, pattern detection, and one-command workflow execution for Claude Code, Cursor, and Codex","language":"TypeScript","stars":20,"topics":["activity-tracing","ai-agents","claude-code","developer-tools","mcp","workflow-automation"],"license":"MIT","category":"mcp-servers","readme_excerpt":"The harness with muscle memory. Keyoku watches what you do in Claude Code, Cursor, or Codex, learns your patterns, and turns them into one-command workflows — automatically. Get Started &bull; How It Works &bull; MCP Tools &bull; Architecture &bull; keyoku-engine Get Started Install it once, then wire it up: A global install keeps keyoku on a durable path. Running npx keyoku init from the throwaway npx cache is refused — npm can evict that directory and break the hooks — so install globally first. The init command wires everything automatically: 1. Registers the MCP server — via claude mcp add --scope user , so Claude Code connects on next launch 2. Installs the hooks — activity recording (every Bash/Edit/Write/Read/MCP call), a session-start brief, and prompt-time practice injection 3. Wires Codex too — when /.codex exists, the MCP server lands in config.toml automatically (same tools, same workflows) 4. Stays local — no cloud, no telemetry; state lives in /.keyoku with the same file permissions as /.aws . keyoku pause stops everything instantly. Restart Claude Code and keyoku is live. Then skip the cold start entirely: Now ask your agent to run workflow suggest — keyoku mines your real history immediately instead of waiting days for new activity. Approved workflows appear as native slash commands (MCP prompts), and keyoku export bakes one into your repo as a Claude Code skill your whole team inherits. How It Works Without Keyoku: you describe the same multi-step process to ","default_branch":null,"files":null,"tree":[],"storefront":"/r/Keyoku-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Keyoku-ai/keyoku/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}