Both are open source memory options with comparable terms, so the choice comes down to which model of the problem you prefer — compare the descriptions below rather than the licence.
Memory primitives that plug straight into LangGraph checkpoints.
Builds a graph + vector memory layer over your agent's history and documents.
| LangMem | Cognee | |
|---|---|---|
| Licence | Open source | Open source |
| Pricing | open source | open source |
| Self-hostable | Yes | Yes |
| Languages | Python | Python |
| Install | pip install langmem | pip install cognee |
| Keys required | None | None |
Both are open source memory options with comparable terms, so the choice comes down to which model of the problem you prefer — compare the descriptions below rather than the licence. LangMem: Memory primitives that plug straight into LangGraph checkpoints. Cognee: Builds a graph + vector memory layer over your agent's history and documents.
LangMem can run on your own infrastructure. Cognee can run on your own infrastructure.
LangMem is open source (open source). Cognee is open source (open source).
Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.
curl -s -H "Accept: text/markdown" https://newagent.build/compare/langmem-vs-cognee