Potencialize seu agente
Instalação do publicador. Não é um endpoint do PlugMCP.
Host a copy with our keys and logs.
Ainda não há uma versão empacotada no registro. Siga o README do repositório.
URL remota ou um comando na sua máquina? Como as duas instalações diferem
Rodar no PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirPiper Morgan is a Python-based product management assistant that turns routine PM work—standup notes, backlog triage, status updates, roadmap questions—into natural conversation, backed by AI analysis that surfaces strategic insight rather than just storing tickets. It's built for product managers and small teams who want an assistant that reasons about their work instead of adding another dashboard to check. What sets it apart is its conversational-first design: instead of bolting a chat window onto a tracker, Piper Morgan treats dialogue as the primary interface and uses it to drive analysis, so context accumulates naturally over time rather than being re-entered into forms. This repository is v1.0 of the project and the canonical source for development.
# Illustrative usage shape — see the technical reference for current APIs
assistant = PiperMorgan()
response = assistant.ask("Summarize open issues by priority and flag anything at risk this sprint")
print(response.insights)
Feature availability tracks the alpha program; consult pmorgan.tech for the current, authoritative capability list.
Piper Morgan is a Python application that sits between you and the tools you already use. It receives natural-language requests, figures out what you're trying to accomplish, and orchestrates the appropriate actions through a layered pipeline. The core flow looks like this:
User request (chat or CLI)
│
▼
┌───────────────────────┐
│ Intent & Context │ Parses the request, resolves references
│ Resolution │ (projects, tickets, people)
└──────────┬────────────┘
▼
┌───────────────────────┐
│ Orchestration Layer │ Selects and sequences the right
│ │ handler(s) for the task
└──────────┬────────────┘
▼
┌───────────────────────┐
│ Tool & Integration │ Talks to issue trackers, docs,
│ Adapters │ calendars, repos, etc.
└──────────┬────────────┘
▼
┌───────────────────────┐
│ Reasoning & │ Summarizes, prioritizes, drafts,
│ Synthesis │ or answers using the gathered data
└──────────┬────────────┘
▼
Structured response + optional follow-up actions
Managed via the project's dependency manifest. The core runtime needs:
fastapi — HTTP API layeruvicorn — ASGI serversqlalchemy — ORM and migrationsalembic — schema versioningpydantic — settings and request/response modelshttpx — outbound HTTP clientpython-dotenv — environment file loadingDevelopment extras (linting, tests) are declared in the same manifest.
Before first launch, you must supply values for the settings below (see the Configuration section for full details):
DATABASE_URL=postgresql://user:password@localhost:5432/piper_morgan
LLM_PROVIDER_API_KEY=<your-provider-key>
LLM_MODEL=<provider-model-identifier>
DATABASE_URL must point to a reachable PostgreSQL instance with permission to create tables.LLM_PROVIDER_API_KEY is validated on startup; the app exits with a diagnostic if absent.Outbound HTTPS access is required to the configured LLM provider. If you run behind a proxy, set HTTPS_PROXY in the environment before starting the app.
Piper Morgan reads its configuration from environment variables, optionally seeded from a local .env file. Copy the provided .env.example to .env and fill in the values relevant to your setup. Variables not set fall back to the defaults noted below.
At least one provider must be configured for AI-backed features to work. Each provider is enabled by supplying its key.
.env# Environment
PIPER_ENV=development
PIPER_LOG_LEVEL=INFO
PIPER_DATA_DIR=./data
# AI provider (pick one or both)
ANTHROPIC_API_KEY=
OPENAI_API_KEY=
PIPER_DEFAULT_PROVIDER=anthropic
PIPER_MODEL=
PIPER_MAX_TOKENS=2048
# Storage
DATABASE_URL=sqlite:///./data/piper.db
Configuration is resolved in the following order, with each layer overriding the one before it:
.env file (or the file at PIPER_CONFIG_PATH)This means shell-exported variables always win over .env entries, which is useful for CI and containerized runs.
.env. It is listed in .gitignore; keep secrets out of version control..env is required in production.DATABASE_URL at a server-backed database for multi-user or production use.Is Piper Morgan a hosted service or something I run myself?
Piper Morgan is a Python application you run in your own environment. The hosted alpha at pmorgan.tech is a convenience for testers; everything else runs locally.
What do I actually need before it will start?
config.yaml (see the Configuration section)Why won't it start / why do I get a config error?
Most startup failures trace back to missing or malformed config. Run the config check first, then verify provider connectivity:
from piper_morgan.config import load_config, validate
cfg = load_config("config.yaml")
validate(cfg) # raises with the specific field that's missing
Can I use it without an LLM provider?
No — the assistant's core loop requires a provider. You can point it at a local model to keep everything offline, but you still need to configure one.
Which Python versions are supported?
See the pyproject.toml / requirements.txt for the exact lower bound. At minimum, Python 3.11 is required; anything older is unsupported and untested.
How does it differ from a task tracker like Jira or Linear?
Piper Morgan sits alongside those tools rather than replacing them. It handles the conversational and analytical sides of PM work — drafting, summarizing, surfacing insights — not backlog storage or sprint boards.
Can I run it in a container?
Yes, a Dockerfile ships with the repo. The same configuration requirements apply; mount your config.yaml and provide provider/database access via environment variables.
Where do I report bugs or ask questions?
I forked the project — what should I keep?
If you want your fork to be recognizably Piper Morgan, read docs/legal/values.md first. It describes the behaviors and boundaries that define the project.
Is it production-ready?
It's at v1.0 and under active development. Use it, file issues, and treat production deployment as your own assessment.
This project is released under the Apache License 2.0. The full license text ships with the repository as LICENSE and is also available at apache.org/licenses/LICENSE-2.0.
When redistributing, a reasonable attribution header looks like:
Piper Morgan - Intelligent Product Management Assistant
Copyright (c) the Piper Morgan contributors
Licensed under the Apache License, Version 2.0
See the LICENSE file in the project root for the full text.
Forking is explicitly permitted. For a fork to be recognizably Piper Morgan, follow the Project Values guidance; the license itself places no restriction on independent forks beyond the notice requirements above.
By submitting a contribution (pull request, patch, or otherwise), you agree that your contribution is licensed under the same Apache License 2.0 terms, per Section 5 of the license. No separate CLA is required.
For licensing questions not covered here, open an issue via GitHub Issues or consult the canonical text at apache.org/licenses/LICENSE-2.0.
Piper Morgan Product: Intelligent Product Management Assistant for Python
Ferramentas
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Este registro não lista nenhuma variável de ambiente obrigatória.
Piper Morgan Assistant roda localmente via stdio.
Última verificação: 2026-10-27. Piper Morgan Product: Intelligent Product Management Assistant for Python