Flowise vs Graphiti

Flowise is an open source platform for building generative AI agents and large language model workflows. Its Assistant, Chatflow, and Agentflow visual builders cover assistants, chatbots, single- and multi-agent systems, and workflow orchestration. Listed capabilities include execution logs, visual debugging, evaluations, human review, and retrieval-augmented generation indexing pipelines. Documentation describes connections to more than 100 sources, tools, vector databases, and memories, including LangChain, LlamaIndex, and Zapier Zaps. Developers can use APIs, an embedded chat widget, and TypeScript or Python SDKs. Deployment options include cloud and on-premises setups, as well as self-hosting through npm or Docker. Listed security controls include role-based access, single sign-on, encrypted credentials, secret managers, rate limiting, and restricted domains. The project is winding down: active feature development ceased July 29, 2026; repository archival is listed for August 10; and end of life is August 31, 2026. Source code remains under Apache 2.0. Free costs nothing; Starter costs $35 a month.

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.