| Devrag | Cognee | |
|---|---|---|
| Description | Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multiling... | Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources |
| Category | Knowledge & Memory | Knowledge & Memory |
| Language | Go | Python |
| License | — | Apache-2.0 |
| Stars | 46 | 14993 |
| Website | https://github.com/tomohiro-owada/devrag | https://www.cognee.ai |