Context Engineering Platform (Zep v3) built on Graphiti — a bi-temporal knowledge graph that models facts as triplets (entity-relationship-entity) with temporal metadata on every edge. Contradictions are resolved via temporal edge invalidation, not LLM judgment: when a fact changes, the old edge is superseded and a new one is created, preserving the full historical timeline. Ingestion uses discrete episodes (text or structured JSON) that maintain data provenance and enable incremental extraction. Zep Cloud delivers enterprise-grade managed hosting (SOC 2 Type II, HIPAA BAA, BYOC); Graphiti is the Apache-2.0 OSS engine underneath.
Deep diveZep deep dive: how Graphiti's bi-temporal knowledge graph actually worksRead →- Storage
- Zep Cloud (fully managed, three modes: Cloud / Cloud+BYOK / BYOC); OSS: Neo4j 5.26+, FalkorDB 1.1.2+ (Redis-based), Amazon Neptune (Database Cluster or Analytics Graph); Kuzu 0.11.2 supported but deprecated (upstream unmaintained as of v0.29.x)
- Retrieval
- Hybrid: vector similarity (semantic) + BM25 full-text search + graph traversal, with distance-based reranking from central entity nodes — no LLM-in-loop reranking step. Supports point-in-time historical queries via archived superseded edges. Zep Cloud p95 < 200 ms at up to 100M graphs.
- Self-host
- Self-host: heavy
- License
- Apache-2.0
- Pricing
- Zep Cloud: free tier (10,000 credits/month, 2 projects); Flex $1,250/yr (50K credits/month, $25/10K overage); Flex Plus $3,750/yr (200K credits/month, webhooks + custom extraction); Enterprise custom (SOC 2 Type II, HIPAA BAA, BYOC). Credit cost: 1 credit per episode up to 350 bytes; retrieval and storage free. Graphiti OSS engine free. · Free + paid
- GitHub stars
- 29,735
- Last release
- 2026-07-27
- Last commit
- 2026-08-05
- First catalogued
- 2026-06-28
Strengths
- Bi-temporal edge invalidation resolves contradictions without LLM judgment — superseded facts are archived not deleted, enabling exact point-in-time historical queries
- Hybrid retrieval (vector + BM25 + graph traversal) with distance-based reranking from central nodes avoids LLM-in-loop latency overhead
- Broad graph DB support: Neo4j, FalkorDB (Redis-based), Amazon Neptune — choose backend by operational preference and cloud environment
- Zep Cloud hits sub-200ms p95 retrieval at 100M graph scale and reports 94.7% on LoCoMo; SOC 2 Type II + HIPAA BAA for regulated workloads
- Episodic ingestion with per-episode provenance; accepts both unstructured text and structured JSON in the same graph
Watch out
- Self-hosting requires a dedicated graph DB (Neo4j 5.26+ or FalkorDB + Redis) plus LLM and embedding provider config — significant operational footprint; Zep Community Edition was deprecated
- Kuzu backend officially deprecated in v0.29.x (upstream unmaintained); only Neo4j, FalkorDB, and Amazon Neptune are actively supported
- Zep Cloud credit cost is episode-driven (1 credit per 350 bytes ingested); high-ingestion agents can exhaust the free 10K credits/month quickly — cost forecasting requires estimating episode volume
Best for
- Agents tracking facts that change over time — customer profiles, evolving relationships, product details that must stay current without losing history
- Enterprise multi-agent deployments needing SOC 2 / HIPAA compliance, BYOC deployment, and sub-200ms retrieval SLAs
- Workflows requiring point-in-time historical queries ("what did the agent know about X on date Y?")
How it integrates
Benchmark results
| Benchmark | Value | Backbone | Trust | Source |
|---|---|---|---|---|
| longmemeval | 63.8 accuracy | gpt-4o-mini | Self-reported | Zep AI (Rasmussen et al.) ↗ |
| longmemeval | 90.2 accuracy | gpt-5.4 (reasoning=medium) | Self-reported | Zep ↗ |
| longmemeval | 71.2 accuracy | GPT-4o | Independent | Hindsight/Vectorize (competitor re-run) ↗ |
| longmemeval | 58.6 accuracy | gpt-4o-mini | Independent | LiCoMemory (Huang et al., HKUST et al.) — competitor re-run ↗ |
| locomo | 44.76 accuracy | gpt-4o-mini | Independent | LiCoMemory (Huang et al., HKUST et al.) — competitor re-run ↗ |
| locomo | 94.7 accuracy | gpt-5.4 (reasoning=medium) | Self-reported | Zep ↗ |
Sources
- Pricing page re-checked — unchanged: Free 10,000 credits/mo and 2 projects; Flex $1,250/yr ($104/mo billed annually, 50,000 credits/mo, 5 projects); Flex Plus $3,750/yr ($312/mo billed annually, 200,000 credits/mo, 10 projects); Enterprise custom (vendor)
- Monthly card re-verification — GitHub API repo metadata: 29,431 stars, license Apache-2.0 confirmed, archived=false, last commit on the default branch 2026-07-30 (third-party)
- https://www.getzep.com/ (vendor)
- https://github.com/getzep/graphiti (vendor)
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory (Rasmussen et al., Zep AI, Jan 2025) (paper)
- Zep — Context Engineering Platform positioning and temporal KG validity windows (vendor)
- GitHub API — stars 28184, latest release v0.29.2 (2026-06-08), pushed 2026-06-27 (third-party)
- Graphiti MCP server docs — stdio (Claude Desktop) + SSE/HTTP (Cursor IDE, VS Code with Copilot); FalkorDB/Neo4j required; Docker Compose provided (vendor)
- graphiti-core on PyPI — v0.29.2 (Jun 2026); Neo4j/FalkorDB/Neptune backends; OpenAI/Anthropic/Gemini/Groq LLM providers; Voyage AI/SentenceTransformers embedders (vendor)
- getzep/zep-js TypeScript SDK docs — `npm install @getzep/zep-js` (OSS) or @getzep/zep-cloud; LangChain-compatible (vendor)
- Zep Cloud REST API reference (Fern) — threads, graph (nodes/edges/episodes), memory add, and search endpoints; host api.getzep.com (vendor)
- Zep Cloud pricing — re-verified unchanged: free 10K credits/month; Flex $1,250/yr 50K credits; Flex Plus $3,750/yr 200K; Enterprise BYOC + SOC2 Type II / HIPAA BAA (vendor)
- Graphiti LangGraph integration — official docs; per-turn fact retrieval using user entity as anchor; async episode persistence (vendor)
- Graphiti overview — bi-temporal triplet model, episodic ingestion (text+JSON), hybrid retrieval (vector+BM25+graph), Amazon Neptune support confirmed (vendor)
- GitHub API re-check — 28,770 stars, Apache-2.0, pushed 2026-07-15; still v0.29.2 (2026-06-08) as latest tagged release, no new release since prior verification (third-party)
- GitHub API re-check — license still Apache-2.0, not archived, pushed 2026-07-23T19:00Z; v0.29.2 (2026-06-08) still latest release (third-party)
- Zep Cloud pricing re-check — unchanged: Free 10K credits/mo, Flex $1,250/yr (50K credits), Flex Plus $3,750/yr (200K credits), Enterprise custom with SOC 2 Type II + HIPAA BAA + BYOC/BYOK; SOC2/HIPAA still Enterprise-only (vendor)
Last verified 2026-08-01 · updated by refresh-framework-cards