Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Supermemory
Hosted memory and context API plus consumer app: extracts facts, builds user profiles, handles contradictions and forgetting; a local single-machine binary is available.
supermemory.ai/Active
supermemory 5.0.0 SDK on PyPI 2026-10-06; server-v0.0.9 released 2026-10-12; repo pushed 2026-10-25. (checked 2026-10-25)
In Agent memory
Where it stands apart
- How is the main thing licensed? proprietary or closed source (19% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? partly (some features need the maker's servers) (14% of 21 others)
- Who is it for? both (14% of 21 others)
What it shares with most of the community
- Is it actively maintained? active (67% of 21 others)
- How is it mainly sustained? company with a paid product, tier, or ads (75% of 20 others)
- In the default setup, who mainly decides what gets remembered? the system, by extracting memories from conversations or data in the background (67% of 21 others)
- By default, how do old or wrong memories mainly go away? the system updates, merges, or decays them automatically (58% of 19 others)
- Does it work with models from different LLM vendors? yes, model-agnostic (86% of 21 others)
- Is there a first-party MCP server for it? yes (67% of 21 others)
- How is memory separated between users or tenants? built-in scoping by user, agent, session, or tenant IDs (62% of 21 others)
- Does it publish scores on public memory benchmarks (LoCoMo, LongMemEval, BEAM, etc.)? yes (62% of 21 others)
Nearest neighbors
- MemOS (MemTensor) 76% of 17 shared answers match
- Zep 71% of 17 shared answers match
- Honcho 65% of 17 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | stands apart proprietary or closed source Repo is MIT but contains SDKs, web app, MCP and docs; the memory engine is not in the public repo. Local binary is 'free within its lite license limit'. | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | stands apart partly (some features need the maker's servers) 'npx supermemory local' runs the full Memory API on one machine; connectors, multi-member orgs and dashboard are Enterprise/cloud only. | source 2026-10-25 |
| Do you need an account to use it? | optional account Local binary prints its own API key, no account; hosted console is the other path. | source 2026-10-26 |
| Who is it for? | stands apart both Developer API plus consumer app and assistant plugins. | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | none of these (its own format or interface) Own hosted API and graph engine. | source 2026-10-26 |
| In the default setup, who mainly decides what gets remembered? | the system, by extracting memories from conversations or data in the background | source 2026-10-25 |
| How can the person the memories are about see and edit them? | directly, as readable files or in a UI they control Consumer app shows and edits memories. | source 2026-10-25 |
| By default, how do old or wrong memories mainly go away? | the system updates, merges, or decays them automatically 'Handles temporal changes, contradictions, and automatic forgetting.' | source 2026-10-25 |
| Where do memories live in the default setup the docs lead with? | in the vendor's cloud | source 2026-10-25 |
| Does it work with models from different LLM vendors? | yes, model-agnostic | source 2026-10-25 |
| What is the main storage model for long-term memory? | knowledge graph (usually with vectors alongside) Graph engine plus user profiles and hybrid search. | source 2026-10-25 |
| What shape does it mainly take (the one its docs lead with)? | memory service (self-hosted server or hosted API) | source 2026-10-25 |
| Is there a first-party MCP server for it? | yes | source 2026-10-25 |
| How is memory separated between users or tenants? | built-in scoping by user, agent, session, or tenant IDs Container tags / user profiles. | source 2026-10-25 |
| Does it publish scores on public memory benchmarks (LoCoMo, LongMemEval, BEAM, etc.)? | yes Claims #1 on LongMemEval, LoCoMo, ConvoMem; maintains MemoryBench. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/supermemoryai/supermemory · read 2026-10-25
- Web page · supermemory.ai/ · read 2026-10-25
- Web page · supermemory.ai/docs/self-hosting/local-vs-enterprise · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.