Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Graphiti
Open-source temporal knowledge graph framework from Zep: builds bi-temporal entity/fact graphs from episodes, on Neo4j, FalkorDB, Neptune or Kuzu.
graphiti-core v0.31.2 released 2026-10-20; repo pushed 2026-10-25. (checked 2026-10-25)
In Agent memory
Where it stands apart
- Which shared standard or format does it mainly build on? a property-graph database (Neo4j, FalkorDB, Kuzu) (14% of 21 others)
- By default, how do old or wrong memories mainly go away? they stay but are marked superseded (old facts are kept) (16% of 19 others)
What it shares with most of the community
- Is it actively maintained? active (67% of 21 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (67% of 21 others)
- How is it mainly sustained? company with a paid product, tier, or ads (75% of 20 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)
- 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
- Cognee 88% of 17 shared answers match
- Mem0 76% of 17 shared answers match
- LongMemory (formerly OpenMemory) 75% of 16 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) Apache-2.0 | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Zep's open-source engine; Zep sells the managed version. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes Bring your own graph DB and LLM. | source 2026-10-25 |
| Do you need an account to use it? | no account pip install; bring your own graph DB and LLM. Zep platform is separate and optional. | 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, FalkorDB, Neptune or Kuzu. | 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 LLM extracts entities and facts from added episodes. | source 2026-10-25 |
| How can the person the memories are about see and edit them? | only through developer APIs or a developer dashboard Graph DB tools and APIs; reference servers have no auth. | source 2026-10-25 |
| By default, how do old or wrong memories mainly go away? | stands apart they stay but are marked superseded (old facts are kept) 'invalidated — not deleted. Query what's true now, or what was true at any point in time.' | 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 | 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? | yes Reference MCP server in mcp_server/. | source 2026-10-25 |
| How is memory separated between users or tenants? | built-in scoping by user, agent, session, or tenant IDs group_id partitions graphs; README warns servers do not enforce tenant auth. | source 2026-10-25 |
| Does it publish scores on public memory benchmarks (LoCoMo, LongMemEval, BEAM, etc.)? | yes Zep paper (DMR, LongMemEval) evaluates the Graphiti engine. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/getzep/graphiti · read 2026-10-25
- Web page · arxiv.org/abs/2501.13956 · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.