Autonomous Agent Harness

This turns Claude Code into a persistent autonomous agent by wiring together crons, dispatch, memory, and computer use. Instead of running a separate framework like AutoGPT or Hermes, you schedule recurring tasks that review PRs, monitor deploys, or run daily standups using Claude's native scheduled-tasks MCP server. Memory persists across sessions through both built-in project memory files and the knowledge graph MCP server. The architecture is clever: task queues live in markdown files, cron patterns trigger agent sessions, and computer-use handles browser automation. Best for when you want Claude to keep working between conversations, like nightly test runs or hourly production checks, without spinning up external infrastructure.

Install to Claude Code

npx -y skills add affaan-m/ecc --skill autonomous-agent-harness --agent claude-code