Supermemory
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
Supermemory scores 7.8/10 (Strong) in RAG & Memory.
Language TypeScript License MIT Stars 28.1k★ Type service Self-host Yes Repo supermemoryai/supermemory Homepage https://supermemory.ai
Quality
Strong 7.8
Adoption 61
Activity 82
Maturity 93
Community 60
Capability 85
Show the math
Overall 7.8/10
value = 7.8/10
score = value
Adoption 6.5/10
value = 61.2/100
score = 1 + 9 * value / 100
Activity 8.4/10
value = 82.4/100
score = 1 + 9 * value / 100
Maturity 9.3/10
value = 92.7/100
score = 1 + 9 * value / 100
Community 6.4/10
value = 60.1/100
score = 1 + 9 * value / 100
Capability 8.7/10
value = 85.4/100
score = 1 + 9 * value / 100
Key metrics
28.1k★ GitHub stars
260/90d Recent commits
21 devs/90d Recent contributors
LongMemEval 85.4% LongMemEval-s accuracy ~85.4% accuracy on LongMemEval with sub-300ms retrieval, per Supermemory's own research/blog (supermemory.ai/research, supermemory.ai/blog/supermemory-vs-zep). Vendor-published, gpt-4o.
2.3y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
- Managed option
Managed option
Available as a hosted/managed service in addition to self-hosting.
memory vector-graph api agents