Home Projects graphjin
graphjin
Go

graphjin

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

by dosco · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
agentic-aiai-agentscloud-nativeApache-2.0Go
View on GitHub
In plain words

Manage and control AI agents' access to your company's databases, files, and APIs through a single governed graph.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
graphjin — GitHub preview card
📈 Star history
3.2k3.1k
2026-07-122026-08-31
📈 Track graphjin

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

graphjin has 3.2k stars on GitHub. It has been forked 194 times. graphjin is written mainly in Go. It has been in active development since 2019. graphjin is available under the Apache-2.0 license. Its main topics are agentic-ai, ai-agents, cloud-native, cockroachdb.

Frequently asked questions

What is graphjin?

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

Is graphjin open source?

graphjin is an open-source project. It is released under the Apache-2.0 license.

Is graphjin free?

Yes. graphjin is free and open source — you can use, modify and self-host it.

What license does graphjin use?

graphjin is available under the Apache-2.0 license.

What language is graphjin written in?

graphjin is written mainly in Go.

🏅 Maintainer of this project?
olud.ai badge — graphjin

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=dosco-graphjin)](https://olud.ai/project/dosco-graphjin.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.