{
  "markdown": "# Progi - MCP-native Workflow Engine\n\n<img src=\"docs/images/logo/progi-logo-small.png\" alt=\"Progi\" width=\"120\" />\n\nProgi teaches your agent how **you** like to get things done. So you can do your best work without re-explaining your process or losing context between sessions.\n\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![PyPI](https://img.shields.io/pypi/v/progi)](https://pypi.org/project/progi/)\n[![MCP](https://img.shields.io/badge/MCP-compatible-6366f1)](https://modelcontextprotocol.io)\n\n---\n\n## Get started\n\nAdd Progi to your MCP client config (GH Copilot / Cursor / Claude Code / etc):\n\n```json\n{\n  \"mcpServers\": {\n    \"progi\": {\n      \"command\": \"uvx\",\n      \"args\": [\"progi\"]\n    }\n  }\n}\n```\n\nProgi Monitoring starts automatically at `http://127.0.0.1:8000`.\n\nIf you want to start Monitoring on a different port:\n```json\n{\n  \"mcpServers\": {\n    \"progi\": {\n      \"command\": \"uvx\",\n      \"args\": [\"progi\"],\n      \"env\": {\n        \"PROGI_WEB_PORT\": \"8080\"\n      }\n    }\n  }\n}\n```\n\n---\n\n## How it works\n\n**1. Describe your workflow**\n\n*\"Hey Progi, help me create workflow for creating integrations, reviewing code, and publishing PRs.\"*\n\nDescribe your process in plain language. You can be detailed or just provide a rough idea. Progi stores it as a structured workflow with per-step playbooks.\n\n**2. Run tasks, stay in the loop**\n\n*\"Hey Progi, start a new task, we need to review a new docs PR in the repo.\"* \nYour agent loads the workflow, works through each step using your playbooks, and loops you in at critical checkpoints to review output.\n\n**3. Monitor progress**\n\nProgi Monitoring gives you a live view of every running and completed task — status, progress, and the full output history across all your workflows.\n\n**4. Optimize as you go**\n\nTweak playbooks in Progi Monitoring between runs. Because workflows live in a database and survive context resets, every future task picks up your changes automatically — your process gets sharper with each iteration.\n\n---\n\n## MCP Tools\n\n### Work loop\n\n| Tool | Description |\n|---|---|\n| `create_task` | Create a new task under a given workflow (status `todo`); returns a preview of its first step |\n| `list_tasks` | List tasks, optionally filtered by status and/or workflow |\n| `start_or_continue_task` | Main work-loop entry point — starts or resumes a task and returns the current step's playbook, input data, and output spec |\n| `update_progress_notes` | Overwrite a task's progress notes (mid-step save point) |\n| `finish_step` | Mark the current step complete, store its output, and advance to the next step (or mark done) |\n\n### Workflow authoring\n\n| Tool | Description |\n|---|---|\n| `get_process_skeleton_prompt` | Return the Pass 1 system prompt for turning a plain-language description into a structured workflow skeleton |\n| `get_playbook_authoring_prompt` | Return the Pass 2 system prompt for authoring a step's playbook (injects workflow context) |\n| `save_workflow` | Persist a new workflow, its steps, and playbooks |\n| `list_workflows` | Return all workflows with their ordered steps |\n\nAuthoring is two passes: Pass 1 turns a plain-language description into a structured skeleton; Pass 2 authors each step's playbook. `save_workflow` persists both.\n\n---\n\n## Configuration\n\n| Variable | Default | Purpose |\n|---|---|---|\n| `PROGI_DB_PATH` | OS data dir (`platformdirs`) | SQLite file location |\n| `PROGI_WEB_HOST` | `127.0.0.1` | Web UI bind host |\n| `PROGI_WEB_PORT` | `8000` | Web UI port |\n| `PROGI_NO_WEB` | `0` | Set to `1` to disable the web UI |\n\nRun modes: `uvx progi` (MCP + web UI), `uvx progi --no-web` (MCP only), `uvx progi-web` (web UI only).\n\n> Use an absolute path for `PROGI_DB_PATH`\n\n\n<!-- mcp-name: io.github.zseta/progi -->",
  "bytes": 3755,
  "sha": "bc8f3ffc0e1fccc6484eebe7e6e778743ec579599ec8a383f60978be7f92435e",
  "repo_slug": "zseta/progi",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_zseta_progi_006c434f/readme"
}