agent-workspace-architecture

jimy-r/agent-workspace-architecture

★ 2 stars Python 🤖 AI/LLM Updated 1d ago

Blueprint for a personal agent workspace — personas, routines, hooks, skills, MCP servers, memory, task coordination. Worked example in Claude Code; patterns generalise.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agent-workspace-arch": {
      "command": "uvx",
      "args": [
        "agent-workspace-architecture"
      ]
    }
  }
}

Or install with pip: pip install agent-workspace-architecture

README Excerpt

A blueprint for a personal **agent workspace** — personas, routines, hooks, skills, MCP servers, memory, and task coordination. This repo's worked example is built in [Claude Code](https://claude.com/claude-code) (so the file conventions you'll see — `CLAUDE.md`, `.claude/skills/`, MCP config — are Claude-Code-specific), but the *patterns* (roles library, memory hygiene, audit cadence, classify-then-act heartbeat, dead-man's-switch, tier classification by mechanical impact) port to any agent sub

Topics

agent-workspaceagentsanthropicclaudeclaude-codedocumentationmcpworkspace

agent-workspace-architecture

Quick Install

README Excerpt

Topics

Related AI/LLM Servers