Graphiti vs Ragen
Graphiti
github.comRagen
ragen.aiSide by side
| Figure | Graphiti | Ragen |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 2 |
| Spec score · Retrieval-Augmented Generation Tools | 8.5 (#7) | 7.6 (#19) |
| Purpose | Graphiti is an open-source framework for building and querying temporal context graphs for AI agents. | Ragen answers questions from a company's documents and tools, with citations to the source. |
Plans
In their own words
Graphiti
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.
Ragen
Ragen is a company knowledge assistant available through web, API, or self-hosting. It answers questions using company documents and connected tools, and includes citations to the source material. Teams can create separate assistants for departments such as HR, sales, compliance, customer service, and operations. A website chatbot handles product and policy questions continuously and can be embedded on permitted domains with one line of code. Ragen exposes knowledge to agents through MCP, an OpenAI-compatible API, and a TypeScript SDK. Integrations listed include Google Drive, HubSpot, ClickUp, Fireflies.ai, Google Calendar, Gmail, Slack, Notion, Google Analytics, WooCommerce, Open Mercato, and Rejestr.io; BaseLinker and KSeF are marked coming soon. Ragen Brain organizes documents into knowledge pages, flags contradictions and outdated files, and requires human approval before publishing. File and folder permissions are checked for every answer. Data remains on the customer’s infrastructure, with optional encryption keys and masking for specified identifiers.