Tandem

Tandem is the authority layer for AI-first work: scoped execution, governed tools, approval gates, permissioned memory,

MCP Servers

6.5 /10

Open Source

Visit Website GitHub

Last Updated

2026-06-15

GitHub Stars

109

About Tandem

Tandem is the authority layer for AI-first work. It is a source-available governed runtime that gives solo builders, startups, and platform teams a deployable authority layer controlling what agents can see, which tools they can discover, which actions they can execute, when humans must approve, and what evidence survives.

Our Verdict

A mcp server that is open-source and self-hostable backed by 109 GitHub stars. Tandem is the authority layer for AI-first work: scoped execution, governed tools, approval gates, permissioned memory, and durable evidence..

Features

Entrypoints are clients, not separate engines

Governed tool execution

Tenant-aware runtime

Deployable where the data lives

Provider agnostic

Company knowledge and memory

Detailed Ratings

Ease of Use

6.2

Value for Money

6.7

Features

6.5

Support

5.9

Performance

6.6

Overall Rating

6.5 /10

Pros & Cons

Pros

Open-source — fully self-hostable and auditable
Growing open-source adoption (109 stars)
Entrypoints are clients, not separate engines
Governed tool execution

Cons

Requires technical setup; less hand-holding than managed alternatives
Limited third-party reviews and benchmarks

Use Cases

MCP integrationTool extensionContext retrievalAgent connectivity

Who Is It For?

Teams and individuals looking for extending AI agent capabilities via MCP who value open-source flexibility and control.

#agentic-workflow#anthropic#governed-execution#help-wanted#human-in-the-loop#why

Frequently Asked Questions

What is Tandem?

Tandem is the authority layer for AI-first work. It is a source-available governed runtime that gives solo builders, startups, and platform teams a deployable authority layer controlling what agents can see, which tools they can discover, which actions they can execute, when…

How much does Tandem cost?

Tandem is open-source and free to self-host. See https://github.com/frumu-ai/tandem for installation instructions.

Is Tandem open source?

Yes — Tandem is open source with 109 stars. The source code is on GitHub at https://github.com/frumu-ai/tandem.

Who should use Tandem?

Teams and individuals looking for extending AI agent capabilities via MCP who value open-source flexibility and control.

Related Agents

Deep Research

Use any LLMs (Large Language Models) for Deep Research

Gemini Cli

An open-source AI agent that brings the power of Gemini directly into your terminal

AdWeave — Meta Ads

Meta Ads MCP server with 47 tools for campaigns, creatives, audiences, and insights

Ag2

AG2 is the open-source Python framework for building, orchestrating, and scaling multi-agent AI systems

Links & Resources