#18 · Primary category: Knowledge Base & RAG
graphiti
Build Real-Time Knowledge Graphs for AI Agents
Project last updated:08/29/26
GitHub Stars
30.4K
Forks
3.1K
Contributors
59
License
Apache-2.0
Why we included this project
Graphiti is a good fit when your agent has to keep track of facts that change. It stores knowledge in a temporal graph where each fact carries a validity window and a link back to the source data, so the agent can tell you not just what it knows but when it learned it and where that came from. The graph keeps ingesting new interactions and enterprise data, and superseded facts get marked invalid rather than deleted, which matters for long-running assistants that would otherwise act on stale memory. That makes it useful for customer-facing copilots and support agents, places where flat document chunks or raw chat history don't cut it. There's also an MCP server, so Claude, Cursor, and other MCP clients can query the graph directly.
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
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience