Home/AI Agents/marvin

marvin

PrefectHQ/marvin

an ambient intelligence library

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

22views this month

6.2k stars410 forksLast push Jul 31, 2026 Python Apache-2.0

Decision brief

Python-based ambient AI for agent and chatbot development with LLM interaction, Apache-2.0 licence

Good fit when

You need to develop agents or chatbots that integrate ambient intelligence
Your project requires interacting directly with large language models (LLMs)

Avoid when

You are looking for a framework without direct LLM integration capabilities
Your project does not involve agent or chatbot creation

Observed Jul 14, 2026 · Source: enrich:decision_facts

marvin alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Active (15d since push); As of Aug 16, 2026
Provenance: Not a fork · Organization account; As of Aug 16, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install marvin

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

semantic-kernel

Integrate cutting-edge LLM technology quickly and easily into your apps

Bridge between AI assistants and Unity Editor for asset management, scene control, script editing, task automation

agent-framework

Framework for building and deploying AI agents and multi-agent workflows

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Python-based ambient AI library with capabilities for creating intelligent agents and chatbots that interact with LLMs.

Capability facts

CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 16, 2026
Languages: python
Source: github.language+pyproject.toml · Aug 16, 2026

Categories

Tags

agents ai ambient-ai chatbots gpt llm nli python

README

Installation Marvin is available on PyPI: Configure your LLM provider (Marvin uses OpenAI by default but natively supports all Pydantic AI models): Let Marvin plan a complex workflow tasks = marvin.plan("Create a blog post about AI trends") marvin.run tasks(tasks)

For agents

This page has a .md twin and JSON over the API.

/tools/prefecthq-marvin.md GET /api/graphcanon/tools/prefecthq-marvin GET /api/graphcanon/graph?tool=prefecthq-marvin

Was this helpful?

Anonymous feedback helps us improve pages and translations.