#49 · Primary category: AI Gateway & API Infrastructure

graphjin

agentic-ai ai-agents cloud-native cockroachdb database graphql llm mariadb mcp mongodb mssql mysql oracle postgresql sql sqlite yugabyte

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

Project last updated:08/30/26

GitHub Stars

3.2K

Forks

194

Contributors

56

License

Apache-2.0

Why we included this project

Most agent frameworks assume you will hand the model a connection string and hope for the best. GraphJin takes the opposite route: it compiles plain-language questions into one governed graph over the databases, warehouses, files, and source code a company actually runs, and exposes that graph to agents through GraphQL and the Model Context Protocol. A built-in server-side agent runs the discovery, validation, and execution loop under the caller's own permissions, and every answer is checked against a ledger of what actually ran before it leaves the server. If the agent story is not on your roadmap yet, GraphJin still works as a straightforward GraphQL-to-SQL compiler for existing applications, so adopting it is not a bet on the AI side alone. For teams that want Claude or a custom agent touching production data without raw credentials, this is a solid, auditable middle layer.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category