Directory · head to head
Mem0 vs Supermemory
How their memory differs, from each one’s entry in the directory.
In the directory, which sorts systems by whose memory they hold, Mem0 and Supermemory are both filed under “Building blocks” (also “Memory about you”, “Work & project memory”). Mem0 is partly open source and can keep memory on a server you run or in its maker's cloud; Supermemory is partly open source and can keep memory on your machine or in its maker's cloud. Both list Python, TypeScript, Claude Code, Cursor and Codex among what they work with. Of the 11 mechanisms of human memory, Mem0 has 7 built, 2 partly, 2 not; Supermemory has 5 built (1 in depth), 3 partly, 1 not, 2 not known. Both have built Interference (Mem0: cloud only), Association, Consolidation (Mem0: cloud only), Reconsolidation (Mem0: cloud only) and Gist (Mem0: cloud Pro). Only Mem0 has built Forgetting (cloud, opt-in). Both have partly built Salience and Schemas. Neither has built Prospective. Not known for Supermemory, as its makers' docs don't say: Emotion and Retrieval. Of these, Mem0 has built Retrieval (cloud, opt-in), and hasn't built Emotion.
Measured against human memory
Mem07 built, 2 partly, 2 not
Supermemory5 built (1 in depth), 3 partly, 1 not, 2 not known
built todayLonger = more of it built: a little, partly, built, in depth
Side by side
| Mem0 | Supermemory | |
|---|---|---|
| At a glance | ||
| Whose memory | Building blocks | Building blocks |
| Memory lives | Mem0's cloud, or your own server | Supermemory's cloud, or your own machine |
| API keys | A Mem0 key (cloud) or an AI model key (self-hosted) | A Supermemory key (cloud), or your own AI model key (self-hosted; none with a local model) |
| Works with | Python & TypeScript SDKs, Claude Code, Cursor, Codex, LangGraph, CrewAI | TypeScript & Python SDKs, Claude Code, Cursor, Codex, MCP clients, Vercel AI SDK |
| License | Partly open sourceApache-2.0 | Partly open sourceMIT (repo), Apache-2.0 (SDKs) |
| Price | Free tier; from $19/mo | Free tier; Pro $19/mo |
| Under the hood | ||
| Who writes memories | A separate AI call reads each conversation and pulls out short facts. The AI you talk to doesn't write them. | Supermemory's own model reads what you send and writes the facts, in a background “dreaming” pass. You can steer it with instructions, or write facts yourself. In the plugins, the AI can also save and forget on purpose. |
| Where they're kept | A vector database (about 25 to choose from; Postgres with pgvector self-hosted), plus the names each fact mentions. | Its own engine that mixes meaning search, keyword search and a graph of linked facts. Self-hosted, it all sits in one folder. |
| How they're found | By meaning, by keywords, and by shared names, combined into one ranked list. | By meaning across both facts and original documents, with optional reranking and linked facts. The profile comes along without a search. |
| Extra AI calls | Yes: an AI call to pull out facts on every add, plus embeddings. Dream adds more on the cloud. | Yes: its models read everything you add, billed as credits on the cloud. Self-hosted, those calls run on your model. |
| Measured against human memory | ||
| Mem0 | Supermemory | |
| Of the 11 | 7 built, 2 partly, 2 not | 5 built (1 in depth), 3 partly, 1 not, 2 not known |
| Encoding | ||
| SalienceDecides what's worth keeping, and how much, as a memory is written. | An AI decides what counts as a fact, and you can say what to include or skip. There's no importance score. source | Its model decides what's worth keeping: small talk is less likely to become a lasting memory. There's no visible importance score. source |
| EmotionGives memories written with feeling more weight. | No emotional weighting in the current version. | The engine is closed and the docs don't mention emotional weighting either way. |
| Storage | ||
| ForgettingLets unused memories fade over time on its own. | Once it's switched on for a project, unused memories slowly sink in search results, though nothing is deleted. You can also set expiry dates. source | One-off moments fade unless they matter, and dated facts (“exam tomorrow”) expire. The docs don't say that unused memories fade. source |
| InterferenceWhen a new memory closely matches an old one, notices and lets the newer one win. | Dream marks an older fact as replaced when a newer one contradicts it. Self-hosted, both are kept. source | When a new fact contradicts an old one (a new job, say), the new one wins in search. source |
| Retrieval | ||
| RetrievalRemembering something makes that memory stronger. | Each time a memory comes up in a search, it gets a small boost, once decay is switched on for the project. source | Preferences said again get stronger, but the docs don't say that recalling a memory strengthens it. |
| AssociationLinks memories, so recalling one brings its neighbours. | Memories that mention the same person or thing are linked, and naming it in a question brings them up. source | Facts are linked as they arrive, and a search can bring back each result's linked facts too. source |
| ProspectiveBrings a memory back at the right time without being asked. | It understands “upcoming” when you ask, but nothing comes back on its own. source | Dated facts expire rather than come back, and the profile is always there rather than timed. No reminders are documented. source |
| Transformation | ||
| ConsolidationReworks memories between sessions: strengthening, merging, reorganising. | Dream merges duplicates in the background, and a weekly pass (Pro plan) sums things up. source | “Dreaming” works in the background, grouping related conversations and merging, linking and organising what they say. source |
| ReconsolidationCorrects a memory when it's contradicted, and keeps what it used to say. | A replaced memory stays visible and is linked to what replaced it. source | A replaced fact is kept as history, and editing a memory saves a new version beside the old one. source |
| GistTurns many specific moments into general knowledge. | Dream writes “pattern memories” from things that keep coming up, kept alongside the originals. source | It draws new facts from patterns across many memories. They're marked as guesses and rank lower until approved. source |
| SchemasForms beliefs about people and projects, and weighs new facts against them. | User profiles (beta) keep a summary of each person, but new facts aren't weighed against it. source | Each person or project gets a profile of lasting facts and current context, but new facts aren't documented as weighed against it. source |
The same table on the compare page, where you can add other systems.