StartupSan Francisco, CA · Est. 2023
Zep
Long-term memory for agents, built on temporal knowledge graphs.
Zep maintains durable, time-aware agent memory via its open-source Graphiti engine — facts, relationships and their history — so conversations and tasks can span sessions.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- MetadataBuilt on Graphiti, its Apache-2.0 temporal knowledge-graph engine with about 32k stars, which supports Neo4j, FalkorDB and Amazon Neptune.[1]
- DocsCredits are charged only for ingested Episodes; retrieval, storage, users and threads cost 0 credits.[1]
- DocsEnterprise offers SOC 2 Type II, a HIPAA BAA, bring-your-own-key encryption and bring-your-own-cloud deployment in your VPC.[1]
- DocsThe free trial tier includes 10,000 credits per month for prototyping.[1]
Cons
- DocsZep Community Edition was deprecated and moved to a legacy folder with no updates, so the full Zep service is now available only as cloud or BYOC.[1][2]
- DocsPaid self-serve starts at $125/month (Flex), while SOC 2 Type II, the HIPAA BAA and audit logs are listed as Enterprise-only.[1]
- DocsGraphiti needs an LLM with reliable structured output, and its README warns that other services may cause ingestion failures, especially with smaller models.[1]
- User reportsThe Mem0/Zep LoCoMo dispute leaves neither vendor's headline benchmark score directly comparable.[1]
- Best for
- Agents that need temporally aware, graph-structured memory with enterprise compliance.
- Watch out for
- If you need fully self-hosted memory, plan to build on Graphiti yourself.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Founder & CEO
Context engineering & memory
Their open-source work
Python · ≈33k stars · Apache-2.0
getzep/graphiti
Temporal knowledge graphs for agent memory.
Maintained by Zep
Activity
- Last push
- · yesterday
- Latest release
- v0.31.2
· 4w ago - Last 90 days
- 6 releases
v0.31.2v0.31.2 - update certifi to mitigate eMudhra compromise
· 4w agoWhat's Changed chore(mcp): require graphiti-core 0.31.1 and set MCP version to 1.1.1 by @devin-ai-integration[bot] in https://github.com/getzep/graphiti/pull/2013 chore(ci): add the Devin bot to the CLA allowlist by @danielchalef in https://github.com/getzep/graphiti/pull/2028…
- · 5w ago
What's Changed chore: set graphiti-core version to 0.31.0 for the v0.31.0 release by @devin-ai-integration[bot] in https://github.com/getzep/graphiti/pull/2010 chore: set graphiti-core version to 0.31.1 by @devin-ai-integration[bot] in…
v0.31.0v0.31.0 - gpt-6-luna as the default OpenAI model
· 5w agoWhat's Changed Publish zepai/graphiti on v.. tags like MCP by @mehulp93 in https://github.com/getzep/graphiti/pull/1862 Add pevans to the CLA allowlist [ZEPAI-3570] by @pevans in https://github.com/getzep/graphiti/pull/1883 Update root uv.lock to fix Dependabot alerts…
v0.30.2v0.30.2 - FalkorDB updates
· 2mo agoWhat's Changed fix(ci): bump gh-action-pypi-publish for metadata 2.5 by @prasmussen15 in https://github.com/getzep/graphiti/pull/1821 Bump graphiti-core to 0.30.1 by @prasmussen15 in https://github.com/getzep/graphiti/pull/1822 Fix Neo4j database routing and honor…
mcp-v1.1.0mcp-v1.1.0 - Neo4j Custom Database Fix
· 2mo ago⚠️ Behavior change for existing Neo4j deployments: WHO IS AFFECTED: Self-hosted Neo4j Enterprise deployments where NEO4J_DATABASE (or database: in config.yaml) was set to something other than neo4j. Standard setups using the default neo4j database need no action. Before: The…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
On X
No posts from them in our X feed yet.
In research (7)
- Jetriever: Shifting Agent Memory Retrieval from Similarity to UtilityVerdict: Incremental
Nov 16, 2026 · Zep is listed in the reproduced MAB tables (24.0 overall, Table 7) as a memory-system competitor.
- LEDGER: Auditable Agent Memory Under ChangeVerdict: Useful
Nov 16, 2026 · Named as the closest prior design (temporal knowledge graph with fact validity) but not evaluated.
- Learning to Remember: Advances in Memory Mechanisms for Large Language ModelsVerdict: Incremental
Oct 26, 2026 · Zep/Graphiti is discussed as temporal graph memory.
- Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It RetrievesVerdict: Weak
Oct 23, 2026 · Commercial temporal knowledge-graph memory for agents, a competing approach to agent knowledge layers.
Oct 23, 2026 · Zep's knowledge-graph memory is a baseline in Table 1 (28.1 average) and the main commercial counterpart of this design.
- Remembering Through Change: Provenance-Preserving Hypergraph Memory for Multimodal AgentsVerdict: Incremental
Oct 21, 2026 · Zep's temporal knowledge graph (Rasmussen et al.) is cited as the graph-memory line MHG-Mem builds on.
Showing the 6 newest of 7 papers.
Neighbours in the directory
Berkeley, CA · Est. 2024
Stateful agents with memory, from the team behind MemGPT.
Letta (formerly MemGPT, out of UC Berkeley) builds an agent server with built-in memory, context management and state — letting agents persist, learn and be edited like files rather than living in a chat window.
$10M seed led by Felicis (2024)
San Francisco, CA · Est. 2024
The memory layer for AI apps and agents.
Mem0 (from the EmbedChain team) provides a managed + open-source memory layer that extracts, stores and retrieves user and entity memories across sessions — a standard building block for personalization.
New York, NY · Est. 2023
User modeling and psychology for agent memory.
Honcho is a user-context and memory server that models what each user knows and wants, so agents can personalize without teams hand-rolling their own user-modeling stack.
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintains · 1
- GraphitiProject
Similar entries · 1
- Mem0Startup
Mentioned in · 1
- MemoryTax: The Bitter Lesson of Agent MemoryPaper · 2026-10-21