Graphiti vs RAGFlow

Graphiti is an open-source framework for building and querying temporal context graphs for AI agents. It records validity periods for facts, allowing applications to ask what is true now or what was true at a previous point in time. New structured and unstructured information is integrated incrementally rather than requiring a complete graph rebuild. Derived entities and relationships remain linked to their source episodes for provenance. Retrieval combines semantic search, keyword search, and graph traversal, with result reranking. Developers can define entity and edge types with Pydantic models or let structure emerge from incoming data. Supported graph backends listed by the project are Neo4j, FalkorDB, and Amazon Neptune; Kuzu is deprecated. Graphiti includes FastAPI REST and MCP services, supports several LLM providers, runs locally, and is self-hosted. It requires Python 3.10 or newer and an LLM API key. The Apache-2.0 framework is free.

RAGFlow is an open-source retrieval-augmented generation engine and agent platform for building a context layer for AI agents. Its ingestion pipeline processes multiple data formats into semantic representations for retrieval. Search combines vector search and BM25 with custom scoring and re-ranking, while visual workflows connect retrieval, tools, and MCPs for agent orchestration. Users can connect online, local, and OpenAI-compatible model providers for knowledge bases, chats, search, and agents. Documented connectors include Notion, Google Drive, S3, Microsoft Teams, REST API, and Sitemap. RAGFlow provides HTTP and Python APIs, and a chat assistant can be embedded in another webpage using an iframe. It offers cloud and self-hosted deployment; Docker deployment has a stated minimum of 4 CPU cores, 16 GB RAM, and 50 GB disk. The free plan includes five apps, one team member, 0.1 GB of dataset storage, and 500 monthly credits, but no API key. Starter costs $29 a month and includes an API key.