{"id":29016500,"url":"https://github.com/memgraph/ai-toolkit","last_synced_at":"2025-08-27T11:06:42.306Z","repository":{"id":285702600,"uuid":"958502163","full_name":"memgraph/ai-toolkit","owner":"memgraph","description":"Toolkit for building AI-driven graph apps on Memgraph, with LangChain, MCP, and agent implementations. ","archived":false,"fork":false,"pushed_at":"2025-08-21T12:44:02.000Z","size":798,"stargazers_count":31,"open_issues_count":10,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-08-21T14:31:40.272Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/memgraph.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-04-01T09:54:01.000Z","updated_at":"2025-08-20T01:19:07.000Z","dependencies_parsed_at":"2025-04-16T13:27:33.018Z","dependency_job_id":"9ea61f8f-51c6-4801-bb07-0af479432ef3","html_url":"https://github.com/memgraph/ai-toolkit","commit_stats":null,"previous_names":["memgraph/ai-toolkit"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/memgraph/ai-toolkit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/memgraph%2Fai-toolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/memgraph%2Fai-toolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/memgraph%2Fai-toolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/memgraph%2Fai-toolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/memgraph","download_url":"https://codeload.github.com/memgraph/ai-toolkit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/memgraph%2Fai-toolkit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272324156,"owners_count":24914359,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-27T02:00:09.397Z","response_time":76,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-06-25T22:30:28.915Z","updated_at":"2025-08-27T11:06:42.297Z","avatar_url":"https://github.com/memgraph.png","language":"Python","readme":"# Memgraph AI Toolkit\n\nA unified mono-repo for integrating AI-powered graph tools on top of [Memgraph](https://memgraph.com/).  \nThis repository contains the following libraries:\n\n1. [**memgraph-toolbox**](/memgraph-toolbox/)\n   Core Python utilities and CLI tools for querying and analyzing a Memgraph database. The package is available on the [PyPi](https://pypi.org/project/memgraph-toolbox/)\n\n2. [**langchain-memgraph**](/integrations/langchain-memgraph/)\n   A LangChain integration package, exposing Memgraph operations as LangChain tools and toolkits. The package is available on the [PyPi](https://pypi.org/project/langchain-memgraph/)\n\n3. [**mcp-memgraph**](/integrations/mcp-memgraph/)\n   An MCP (Model Context Protocol) server implementation, exposing Memgraph tools over a lightweight STDIO protocol. The package is available on the [PyPi](https://pypi.org/project/mcp-memgraph/)\n\n4. [**agents**](/integrations/agents/) ⚡ **Experimental**\n   An intelligent database migration agent that automates the process of migrating from MySQL to Memgraph using LLM-powered graph modeling and analysis. Features automated schema analysis, intelligent graph modeling with interactive refinement, and data migration with validation.\n\n## Key Features\n\n### Migration Agent Capabilities\n\n- **🔍 Intelligent Schema Analysis**: Automatically analyzes MySQL database structure and relationships\n- **🧠 LLM-Powered Graph Modeling**: Uses AI to create optimal graph models from relational schemas\n- **🔄 Interactive Refinement**: Allows users to refine graph models through natural language feedback\n- **⚡ Automated Migration**: Handles complete data migration with validation and rollback capabilities\n- **📊 Progress Monitoring**: Real-time migration progress tracking with detailed logging\n- **🛡️ Data Validation**: Comprehensive pre and post-migration data integrity checks\n\n## Usage examples\n\nFor individual examples on how to use the toolbox, LangChain, MCP, or agents, refer to our documentation:\n\n- [Langchain examples](https://memgraph.com/docs/ai-ecosystem/integrations#langchain)\n- [MCP examples](https://memgraph.com/docs/ai-ecosystem/integrations#model-context-protocol-mcp)\n- [Agent migration examples](/integrations/agents/examples/) - Interactive MySQL to Memgraph migration workflows\n\n## Developing locally\n\nYou can build and test each package directly from your repo. First, start a Memgraph MAGE instance with schema info enabled:\n\n```bash\ndocker run -p 7687:7687 \\\n  --name memgraph \\\n  memgraph/memgraph-mage:latest \\\n  --schema-info-enabled=true\n```\n\nOnce Memgraph is running, install any package in “editable” mode and run its test suite. For example, to test the core toolbox:\n\n```\nuv pip install -e memgraph-toolbox[test]\npytest -s memgraph-toolbox/src/memgraph_toolbox/tests\n```\n\n### Core tests\n\nTo test the core toolbox, just run:\n\n```\nuv pip install -e memgraph-toolbox[test]\npytest -s memgraph-toolbox/src/memgraph_toolbox/tests\n```\n\n### Langchain integration tests\n\nTo run the LangChain tests, create a .env file with your OPENAI_API_KEY, as the tests depend on LLM calls:\n\n```\nuv pip install -e integrations/langchain-memgraph[test]\npytest -s integrations/langchain-memgraph/tests\n```\n\n### MCP integration tests\n\n```\nuv pip install -e integrations/mcp-memgraph[test]\npytest -s integrations/mcp-memgraph/tests\n```\n\n### Agent integration tests\n\n```\nuv pip install -e integrations/agents[test]\npytest -s integrations/agents/tests\n```\n\nTo run a complete migration workflow with the agent:\n\n```\ncd integrations/agents\nuv run main.py\n```\n\n**Note:** The agent requires both MySQL and Memgraph connections. Set up your environment variables in `.env` based on `.env.example`.\n\nIf you are running any test on MacOS in zsh, add `\"\"` to the command:\n\n```\nuv pip install -e memgraph-toolbox\"[test]\"\n```\n","funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmemgraph%2Fai-toolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmemgraph%2Fai-toolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmemgraph%2Fai-toolkit/lists"}