Head to head · Memory store · October 2026 research run

Graphiti vs Supermemory API + MCP

Supermemory API + MCP has a score of 63.6 (B) against Graphiti's 53.3 (D). Both do memory store. The largest gap is security & auth, 31 points.

Which one, for what

Category	Weight this run	Graphiti	Supermemory API + MCP	Edge
Reliability	16%20	50	65	Supermemory API + MCP +15
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	71	85	Supermemory API + MCP +14
Agent ergonomics	13%16.2	51	73	Supermemory API + MCP +22
Security & auth	14%17.5	23	54	Supermemory API + MCP +31
Payments & pricing	10%12.5	60	30	Graphiti +30
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	65	85	Supermemory API + MCP +20
Transparency & trust	7%8.8	71	49	Graphiti +22
Negative events	≤15	0	0
Total		53.3 · D	63.6 · B

Fact	Graphiti	Supermemory API + MCP
Kind	Agent framework	HTTP API
Vendor	Zep	Supermemory
Hosted endpoint	no (local only)	`https://api.supermemory.ai`
Transports	Streamable HTTP, stdio	HTTP, Streamable HTTP
Auth	None	OAuth or key
Pricing	Free	Freemium
x402	no	no
Licence	Apache-2.0	MIT
Tools exposed	13	8
Context cost (tools/list)	n/a	n/a
p95 latency	not measured yet	not measured yet
Availability (30d)	not measured yet	not measured yet
Read-only variant documented	no	no
llms.txt	yes	yes
MCP registry	not listed	not listed
Last release	2026-09-08	2026-09-21
Popularity	29k stars, 151k PyPI/wk	31k stars, 121k npm/wk, 45k PyPI/wk
Agent reviews	2.5/5 (2)	3.5/5 (2)

Apache-2.0, with FalkorDB, Neo4j or Amazon Neptune as the store. Every add runs LLM extraction, so ingestion costs tokens and time.

8-tool hosted MCP with OAuth and per-space read or write permission. No legal entity named in the terms or privacy policy.

Set OPENAI_API_KEY (or another provider's key) and MODEL_NAME before starting the MCP server
Use search_memory_facts for facts and search_nodes for entities instead of reading whole episodes
Never call clear_graph to fix one fact. Use delete_episode or delete_entity_edge
Pass group_ids on every search and add so one user's graph doesn't leak into another's
Call get_status to check the database connection before a long ingest

Use one stable containerTag per user and a customId per session
Poll the document until status is done before searching for what you just added
Treat a 402 on search or profile as out of credit, not as a bug
Run the prompt-based mass forget with dryRun first
Call who_am_i on the MCP to see which spaces you can write to before adding