Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Memary
Open-source memory layer for autonomous agents emulating human memory: knowledge graph (Neo4j/FalkorDB) plus memory stream and entity knowledge store.
Last release v0.1.5 and last commit October 2024. (checked 2026-10-25)
In Agent memory
Where it stands apart
- Is it actively maintained? dormant, sunsetting, or archived (14% of 21 others)
- How is it mainly sustained? individual side project, no revenue (0% of 20 others)
- Which shared standard or format does it mainly build on? a property-graph database (Neo4j, FalkorDB, Kuzu) (14% of 21 others)
What it shares with most of the community
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (67% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (67% of 21 others)
- Who is it for? developers (76% of 21 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)
- How can the person the memories are about see and edit them? only through developer APIs or a developer dashboard (62% of 21 others)
- Does it work with models from different LLM vendors? yes, model-agnostic (86% of 21 others)
Not documented
The public sources we read don't say:
- By default, how do old or wrong memories mainly go away?
Nearest neighbors
- A-MEM 69% of 16 shared answers match
- Graphiti 69% of 16 shared answers match
- Cognee 63% of 16 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | stands apart dormant, sunsetting, or archived | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) MIT | source 2026-10-25 |
| How is it mainly sustained? | stands apart individual side project, no revenue Personal-account MIT repo, dormant, no paid product or funding listed. | source 2026-10-26 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-25 |
| Do you need an account to use it? | no account No Memary account; needs third-party keys (OpenAI, Perplexity etc.) and a graph DB. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart a property-graph database (Neo4j, FalkorDB, Kuzu) Neo4j or FalkorDB. | 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? | only through developer APIs or a developer dashboard Streamlit demo dashboard. | source 2026-10-25 |
| By default, how do old or wrong memories mainly go away? | Not documented Not documented. | source 2026-10-25 |
| Where do memories live in the default setup the docs lead with? | in the developer's own infrastructure | source 2026-10-25 |
| Does it work with models from different LLM vendors? | yes, model-agnostic Ollama or OpenAI. | source 2026-10-25 |
| What is the main storage model for long-term memory? | knowledge graph (usually with vectors alongside) | source 2026-10-25 |
| What shape does it mainly take (the one its docs lead with)? | library or API primitive you build into your app | source 2026-10-25 |
| Is there a first-party MCP server for it? | no | source 2026-10-25 |
| How is memory separated between users or tenants? | one store per user or agent; the app partitions it Multiple graphs per agent with FalkorDB. | source 2026-10-25 |
| Does it publish scores on public memory benchmarks (LoCoMo, LongMemEval, BEAM, etc.)? | no | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/kingjulio8238/Memary · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.