dtyq

magic: Build and Manage Enterprise AI Agents

Magic is a self-hostable platform for building AI agents and workflows and connecting them to organizational tools and knowledge. It combines collaboration, approval controls, sandboxing, and budget limits for teams that need managed AI automation.

TypeScriptOther licenseAIAI AgentsSelf Hosted
View on GitHub Compare
Stars
5k
Forks
567
Stars, last 30 days
+40

Our take

Health score

44/100

How it is scored
Activity
52
Community
81
Issues
21
Pull requests
20

+40 stars in the last 30 days

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

5,091

Forks

570

Change since Nov 17, 2026: +1 stars·0 forks

Overview

Magic is an AI agent platform that brings agents, workflows, messaging, and collaborative work into one system. It aims to help individuals and organizations turn AI work into usable deliverables and connect agents with internal systems, rather than relying on standalone chat tools.

It is most relevant when a team needs shared agents, controlled access to business data, human review of sensitive actions, or centrally managed AI usage. The repository provides a self-hosted deployment path as well as links to cloud services.

Key Features

  • Build and use AI agents alongside workflow automation.
  • Connect agents to internal systems such as ERP, CRM, and databases by encapsulating them as reusable digital employees.
  • Render AI output as artifacts such as reports, dashboards, presentations, and spreadsheets.
  • Run agents in sandbox containers with tenant isolation and a network proxy.
  • Require human approval for high-risk actions.
  • Set AI budgets by department, user, and agent.
  • Collaborate on shared projects and report progress to WeCom, DingTalk, or Lark groups.
  • Integrate with Anthropic Skills and OpenClaw Skills, as described by the project.

Use Cases

  • A small team can use agents for recurring work such as customer support, marketing, or data analysis when it wants to extend capacity without adding separate tools for each task.
  • An IT or operations team can expose internal systems and domain knowledge through reusable agents for staff across departments.
  • A company handling sensitive data can evaluate self-hosting, sandbox isolation, and approval workflows to keep automation within managed boundaries.
  • Finance or management teams can connect business data to agents to create reports and dashboards on demand.

Getting Started

The README lists Docker and curl as requirements for self-hosting on macOS or Linux. Run:

curl -fsSL https://getmagicrew.sh | bash

The deployment guide and further setup details are in the repository README.

Alternatives

  • n8n: n8n focuses on visual app-to-app workflows with optional code, while Magic emphasizes managed AI agents with team collaboration, approvals, sandboxing, and budgets.
  • nanobot: nanobot is a lightweight Python framework for personal agents and automation, while Magic targets team-managed agents and workflows connected to organizational tools.
ProjectLanguageLicenseStarsStatus
magicTypeScriptOther5kNot checked yet
n8nTypeScript–209kActive
nanobotPythonMIT48.8kActive

Considerations

  • Self-hosting requires Docker and curl; the README says Windows support is coming soon.
  • The README describes a broad enterprise platform, so teams should assess the deployment and integration work needed for their environment.
  • The repository reports its license as NOASSERTION. The README says the project uses a Magic Open Source License based on Apache 2.0 with additional restrictions, so review the license file before adoption.

Found this useful?

Share it with someone who would like magic.

Comparisons