Cognee vs Supermemory

Pick two tools from the same category to compare side-by-side.

	Cognee Open-source memory platform that gives AI agents persistent long-term memory via combined knowledge graphs and vector embeddings.	Supermemory Closed-source universal memory API that adds long-term, personalized memory to AI agents and apps.
Category	memory	memory
Vendor type	hybrid	commercial
Pricing	freemium	freemium
Strengths	+ Combines graph and vector storage for relationship-aware retrieval beyond similarity search + Provenance tracking on ingested context from files, APIs, and databases + First-party integrations with agent tooling (Claude Code, LangGraph, MCP server) + Pluggable backends for graph, vector, and relational storage	+ Single API covering extraction, profiles, contradiction resolution, and forgetting + Byte-level deduplication lowers cost on repeated agent-loop content + MCP server and integrations for coding-agent memory workflows + Free tier with usage-credit billing across paid tiers
Tradeoffs	− LLM-driven graph construction adds cost and latency to the ingestion pipeline − Younger project with a fast-moving API surface compared to mature retrieval stores − Graph-plus-vector architecture introduces more moving parts than a plain vector memory	− Closed-source proprietary service with no self-hosting − Usage-based pricing can be hard to predict at scale − Benchmark leadership claims are largely self-reported
Used in stacks	0	0