Progi

What is Progi?

Progi is an MCP-native workflow engine that teaches your AI agent your preferred processes. It stores structured workflows with per-step playbooks in a local SQLite database, survives context resets, and provides a monitoring web UI. It is intended for developers who want their agent to follow consistent, reusable procedures across sessions.

How to use Progi?

Describe your workflow in plain language to Progi. It runs a two-pass authoring process to create a structured skeleton and per-step playbooks, then persists everything with save_workflow. Run tasks with create_task, then start_or_continue_task to step through the workflow, and submit_output to advance. Monitor progress via the web UI (default at 127.0.0.1:8000) or disable it with PROGI_NO_WEB=1. Configure database path using the PROGI_DB_PATH environment variable.

Key features of Progi

• Structured workflows with per-step playbooks
• Two-pass authoring from plain-language descriptions
• Persistent storage in a local SQLite database
• Live monitoring web UI for task progress
• Step advancement with output submission
• Playbook updating without re-authoring the entire workflow

Use cases of Progi

• Automating a PR review workflow: create an integration, review code, publish PRs
• Standardizing a recurring maintenance routine across sessions
• Onboarding new team members by codifying team processes
• Running a multi-step data pipeline with human-in-the-loop checkpoints
• Iteratively improving a workflow by tweaking playbooks between runs

FAQ from Progi

What is Progi and how does it differ from basic prompt‑based workflows?

Progi stores workflows as structured steps with playbooks in a persistent database. Unlike plain prompts, these workflows survive context resets, and each future task automatically picks up the latest playbook changes.

How do I configure the database location and the web UI?

Set the PROGI_DB_PATH environment variable to an absolute path (defaults to the OS data directory). The web UI binds to 127.0.0.1:8000 by default; you can change the port with PROGI_WEB_PORT or disable it entirely with PROGI_NO_WEB=1.

Where does Progi store workflow and task data?

All data is stored in a local SQLite database whose location is controlled by PROGI_DB_PATH. No external cloud or server is required.

What transpors does Progi use for communication?

Progi exposes an MCP‑compliant tool interface over stdio (when invoked via the uvx command) plus a web UI for monitoring. It does not provide its own network transport or authentication layer beyond the MCP protocol.

What are the two authoring passes?

Pass 1 converts a plain-language description into a structured workflow skeleton using get_process_skeleton_prompt. Pass 2 authors each step’s detailed playbook using get_playbook_authoring_prompt. The result is persisted with save_workflow.