Skip to content
Back to search

context-graph-plugins

Runtime plugins for Memgraph Context Graph.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/memgraph/ai-toolkit with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/memgraph/ai-toolkit'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/memgraph--ai-toolkit/badge.svg)](/listings/memgraph--ai-toolkit)

HTML

<a href="/listings/memgraph--ai-toolkit"><img src="/api/listings/memgraph--ai-toolkit/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 26 lines
  1. {
  2. "name": "context-graph-plugins",
  3. "owner": {
  4. "name": "Memgraph"
  5. },
  6. "description": "Runtime plugins for Memgraph Context Graph.",
  7. "plugins": [
  8. {
  9. "name": "context-graph",
  10. "source": {
  11. "source": "git-subdir",
  12. "url": "https://github.com/memgraph/ai-toolkit.git",
  13. "path": "context-graph/plugins/memgraph-context-graph-claude"
  14. },
  15. "description": "Capture Claude Code runtime activity through Memgraph Context Graph hooks, and recall past sessions.",
  16. "version": "0.5.10",
  17. "author": {
  18. "name": "Memgraph"
  19. },
  20. "repository": "https://github.com/memgraph/ai-toolkit",
  21. "license": "MIT",
  22. "category": "Productivity",
  23. "tags": ["claude-code", "context-graph", "memgraph"]
  24. }
  25. ]
  26. }
README.md · README · 115 lines · 1 finding marked
  1. # Memgraph AI Toolkit
  2. Python packages for building AI applications with [Memgraph](https://memgraph.com/): agent memory, knowledge graphs, GraphRAG, and framework integrations.
  3. Use the packages independently, or combine them to bring documents, databases, and agent activity into a graph.
  4. [Documentation](https://memgraph.com/docs/ai-ecosystem) · [Examples](#choose-your-starting-point) · [Discord](https://discord.gg/memgraph) · [Issues](https://github.com/memgraph/ai-toolkit/issues)
  5. ## Choose your starting point
  6. | I want to… | Start here |
  7. |---|---|
  8. | Give coding agents memory across sessions and tools | [Context Graph](context-graph/) |
  9. | Extract entities and relationships from documents | [unstructured2graph](unstructured2graph/) |
  10. | Query Memgraph in natural language or build a LangChain agent | [langchain-memgraph](integrations/langchain-memgraph/) |
  11. | Connect an MCP client to Memgraph | [mcp-memgraph](integrations/mcp-memgraph/) |
  12. | Use Memgraph as LightRAG storage | [lightrag-memgraph](integrations/lightrag-memgraph/) |
  13. | Migrate a MySQL or PostgreSQL database into a graph | [sql2graph](agents/sql2graph/) |
  14. | Work directly with Memgraph from Python | [memgraph-toolbox](memgraph-toolbox/) |
  15. | Define and validate a graph's entity and relation types | [hygm](hygm/) |
  16. ## Agent memory with Context Graph
  17. Keep what your agents learn in a database you control. Context Graph captures sessions, tool calls, and skill usage, stores explicit memory, and retrieves relevant past conversations for the next session.
  18. It supports **Claude Code, Codex, Copilot CLI, Cursor, OpenCode, Antigravity CLI, and Grok Build**, plus applications built with the Claude Agent SDK or OpenAI Agents SDK.
  19. ```bash
  20. curl -fsSL https://raw.githubusercontent.com/memgraph/ai-toolkit/main/context-graph/scripts/install.sh | bash
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 29 on GitHub
  21. ```
  22. Setup installs the CLI and connectors, starts its own Memgraph container or connects to one you specify, and wires the agents you select. Docker is needed if setup starts Memgraph for you.
  23. [Get started with Context Graph](context-graph/#getting-started) · [Components](context-graph/#the-components) · [Recall benchmarks](context-graph/eval/#official-numbers)
  24. ## Knowledge graphs from documents
  25. `unstructured2graph` parses documents and extracts entities and relationships. Its default backend, **GLiNER2**, runs locally without an LLM API key; LightRAG is available as an LLM-based alternative.
  26. Start Memgraph:
  27. ```bash
  28. docker run -p 7687:7687 --name memgraph \
  29. memgraph/memgraph-mage:latest --schema-info-enabled=true
  30. ```
  31. Install the package:
  32. ```bash
  33. pip install unstructured2graph
  34. ```
  35. Extract a graph from text:
  36. ```python
  37. import asyncio
  38. from memgraph_toolbox.api.memgraph import Memgraph
  39. from unstructured2graph import from_texts
  40. from unstructured2graph.gliner2_backend import GLiNER2Backend
  41. async def main():
  42. await from_texts(
  43. texts=["Alice works for Acme in London."],
  44. memgraph=Memgraph(),
  45. extraction_backend=GLiNER2Backend(),
  46. enforce_ontology=True,
  47. )
  48. asyncio.run(main())
  49. ```
  50. The extraction model downloads on first use. See [unstructured2graph](unstructured2graph/) for files, URLs, document-format extras, and custom ontologies.
  51. ## Framework integrations
  52. Install only the integration you need:
  53. ```bash
  54. pip install langchain-memgraph # graph store, QA chain, and agent toolkit
  55. pip install mcp-memgraph # MCP server for database queries and schema tools
  56. pip install lightrag-memgraph # LightRAG storage backends
  57. ```
  58. Each package's README covers its connection settings and examples. LLM-based features need credentials for the model provider you choose; local extraction, capture, and recall do not require an LLM key.
  59. ## Developing locally
  60. This is a Python 3.10+ [uv](https://docs.astral.sh/uv/) workspace. From the repository root:
  61. ```bash
  62. uv sync --all-packages --all-extras
  63. uvx ruff@0.16.0 check .
  64. uvx ruff@0.16.0 format --check .
  65. uvx ty@0.0.75 check .
  66. ```
  67. These are the versions CI pins in the [lint workflow](.github/workflows/lint.yaml).
  68. Context Graph, HyGM, and unstructured2graph use an isolated test Memgraph managed by the development script:
  69. ```bash
  70. ./scripts/dev-memgraph.sh test
  71. ./scripts/dev-memgraph.sh test sessions-graph # one package
  72. ./scripts/dev-memgraph.sh test-down # remove the test container
  73. ```
  74. For other packages, see their READMEs and the [test workflow](.github/workflows/tests.yaml) for dependencies and credentials. The [development script](scripts/dev-memgraph.sh) also manages a separate exploration database for dogfooding.
  75. ## Community
  76. Ask questions on [Discord](https://discord.gg/memgraph), report bugs or request features in [GitHub Issues](https://github.com/memgraph/ai-toolkit/issues), and explore the [Memgraph AI documentation](https://memgraph.com/docs/ai-ecosystem).
  77. [MIT license](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.