Mmcp.market

Head to head

Total Agent Memory vs NVIDIA NemoClaw CKG

Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.

Total Agent Memoryio.github.vbcherepanov/total-agent-memory
A
No reviews yet

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

Full listing
NVIDIA NemoClaw CKGio.github.Yarmoluk/ckg-nvidia-nemoclaw
B
No reviews yet

NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.

Full listing

The short version

Neither has been reviewed yet, so the comparison rests on the scan and the public usage numbers. The safety scan favours Total Agent Memory (85/100 against 75). NVIDIA NemoClaw CKG is hosted and callable through the gateway; Total Agent Memory runs on your own machine. Total Agent Memory has noticeably more public adoption.

 Total Agent MemoryNVIDIA NemoClaw CKG
User ratingNo reviews yetNo reviews yet
Safety gradeA85/100B75/100
AdoptionEstablishedNew
GitHub stars68–
Downloads / week166107
Runs whereYour machine (local)Hosted (remote)
Gateway-readyNoYes
Tools—8
Write actions——
Price per callFreeFree
LicenceMITMIT
Last release2026-09-15—
CategoryAI and agentsAI and agents

Other comparisons

Total Agent Memory vs rag-ratTotal Agent Memory vs Basic MemoryTotal Agent Memory vs IWETotal Agent Memory vs Agent RecallTotal Agent Memory vs Fidelis MemoryAll AI and agents servers