Mmcp.market

Head to head

Recall — persistent memory for agents vs Total Agent Memory

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

Recall — persistent memory for agentsdev.workers.notdown-app.recall/memory
C
No reviews yet

Persistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.

Full listing
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

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 60). Recall — persistent memory for agents is hosted and callable through the gateway; Total Agent Memory runs on your own machine. Total Agent Memory has noticeably more public adoption.

 Recall — persistent memory for agentsTotal Agent Memory
User ratingNo reviews yetNo reviews yet
Safety gradeC60/100A85/100
AdoptionNewEstablished
GitHub stars–68
Downloads / week–166
Runs whereHosted (remote)Your machine (local)
Gateway-readyYesNo
Tools5—
Write actions1—
Price per callFreeFree
Licence—MIT
Last release—2026-09-15
CategoryAI and agentsAI and agents

Other comparisons

Recall — persistent memory for agents vs Fidelis MemoryRecall — persistent memory for agents vs coldstartRecall — persistent memory for agents vs GrayMatterRecall — persistent memory for agents vs Basic MemoryRecall — persistent memory for agents vs IWEAll AI and agents servers