dosco/graphjin

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

What it solves

GraphJin provides a unified, governed interface for AI agents to interact with a company's existing fragmented data and systems. Instead of giving agents raw credentials to various databases, warehouses, and files, it creates a single governed graph that allows agents to discover, validate, and execute queries across multiple sources with built-in auditing and security policies.

How it works

GraphJin acts as a compiler and runtime that translates GraphQL and Model Context Protocol (MCP) requests into optimized queries for various backends. It automatically reads database schemas, discovers relationships, and indexes source code using CodeSQL (via tree-sitter). It exposes these systems through a single surface where agents can perform discovery (using a catalog), run queries, and observe runtime status. Every action is checked against an execution ledger before leaving the server.

Who it’s for

It is designed for developers building AI agents that need secure, auditable access to operational databases, data warehouses, object stores (S3/GCS), and source code. It also serves as a high-performance GraphQL-to-database compiler for traditional applications.

Highlights

  • Unified Data Surface: Supports PostgreSQL, MySQL, MongoDB, SQLite, Oracle, MSSQL, Snowflake, Redshift, BigQuery, Cassandra, and object stores (S3/GCS).
  • Built-in Server-Side Agent: Offers a dedicated endpoint that runs the discovery and execution loop internally to return evidence-backed answers.
  • CodeSQL: Indexes source code as a queryable database, allowing agents to link production data to the code that operates it.
  • Governed Access: Implements query allow-lists, read-only boundaries, and policy-aware MCP tools to prevent raw, unguarded access.
  • Real-time Subscriptions: Efficiently handles thousands of concurrent subscribers using batched polling to reduce database load.
  • Durable Memory: Stores saved queries, fragments, and workflows in owner-scoped artifacts.

Related

  • Project
    trailhq/Graft

    Graft is an open‑source TypeScript/Node.js tool that builds a local, markdown‑based knowledge graph of a codebase (summaries, key snippets, typed links) using tree‑sitter for structural parsing and optional LLM summarisation. The graph is cached in a `graft/` folder, refreshed only on file changes, and automatically wired into coding agents like Claude Code, Cursor, Codex, and Gemini. Benchmarks claim up to 46 % fewer tool calls, 42 % token savings, 60 % latency reduction, and a 12‑point correctness boost on SWE‑bench. Integration is via a single `graft init` command that writes agent‑specific instruction files; the CLI also offers search, visualization, and telemetry controls. The project is MIT‑licensed and targets faster, cheaper AI‑assisted development.

  • Project
    CodeGraphContext/CodeGraphContext

    A toolkit and MCP server that indexes local code repositories into a graph database to provide AI agents and developers with structural context like call chains and class hierarchies.

  • Project
    harshkedia177/axon

    A codebase knowledge graph tool that indexes structural dependencies and exposes them via a visual dashboard and MCP tools for AI agents.

  • Project
    vercel-labs/lat.md

    lat.md is an npm‑distributed CLI that creates a markdown‑based knowledge graph for a codebase. It lets you write linked documentation in `lat.md/`, annotate source files with `@lat` comments, and validates the graph. Agents and developers can search it semantically (offline MiniLM or remote OpenAI/Vercel embeddings) and use commands like `lat check`, `lat locate`, and `lat expand` to keep design decisions, constraints, and test specs in sync with the code.

  • Project
    conductor-oss/conductor

    An open-source durable execution platform for microservices and AI agents that turns complex workflow graphs into persisted, inspectable, and recoverable executions.