Source-linked capability map. Zep / Graphiti's product boundary is taken from primary documentation. Protocol-scoped LoCoMo evidence is disclosed. No pricing comparisons.
Product boundary taken from Zep's primary repository and Graphiti documentation. Verify current behavior from the versioned release documentation before making deployment decisions.
Temporal knowledge graphs, governed context assembly, and enterprise context infrastructure. Graphiti is the open-source Python library for building temporal knowledge graphs. Zep Cloud provides a managed service. The Community edition is self-hosted under Apache 2.0.
Choose Zep when: Graph-centric temporal memory is required, complex entity relationships across conversations matter, or managed context infrastructure reduces operational overhead.
Read primary source →Choose SLM when your agents need a local-first operating control plane: SQLite-backed persistent memory, three explicit operating modes, nine npm framework adapters, bounded loops with independent-gate verification, per-workspace RBAC, GDPR Art. 15/17/20 controls, and four integration surfaces — all from one runtime.
Mode A keeps the core memory path local after required assets are present. Mode B adds a configured Ollama endpoint. Mode C adds a configured cloud provider. Optional connectors, proxies, backups, and clients have separate network paths that require independent assessment.
Attributes are configuration-dependent. Review each item independently for your deployment. Zep values are sourced from primary documentation; verify current behavior from the versioned release.
| Capability | SLM V4 | Zep / Graphiti |
|---|---|---|
| Storage layer | SQLite-backed, local-first; configurable data root | Managed service (Zep Cloud) or self-hosted Community edition |
| Graph approach | Graph-derived local state with optional provider paths | Temporal knowledge graph with LLM-based entity extraction (Graphiti) |
| Operating modes | A (local sentence-transformer) / B (Ollama) / C (configured cloud) | Deployment-dependent; verify from release documentation |
| Framework adapters | 9 npm packages (V4) | Python SDK / Graphiti Python library |
| Teams & RBAC | Admin / member / viewer; per-workspace isolation | Organization + user-level memory (Zep Cloud); verify Community edition |
| Bounded loops | Independent-gate verified (V4) | Not separately documented |
| GDPR controls | Art. 15/17/20; hash-chained audit trail; opt-in PII redaction | Verify provider terms for selected deployment |
| EU AI Act self-assessment | Per-mode (self-assessment, not certification) | Not documented |
| Integration surfaces | MCP / CLI / hooks / dashboard | Python SDK / REST API / Graphiti library |
| Published preprints | 3 arXiv preprints (2603.14588, 2603.02240, 2604.04514) | Varies |
| License | AGPL v3 | Apache 2.0 (Community) / Commercial (Zep Cloud) |
Documented in the V4 release. Absent from or not documented in most agent memory systems — verify each for your deployment.
The canonical memory source is SQLite-backed at a configurable data root. No cloud persistence is required for the core memory path in Mode A or B.
Three documented operating modes with distinct embedding paths and network behaviors. Mode can be switched at runtime — memories persist across the transition.
Nine adapter packages published on npm in V4. Adapters provide framework-specific bindings without requiring a rewrite of existing tool configuration.
V4 adds bounded loop orchestration with an independent verification gate at each iteration boundary. Gate results are inspectable via CLI and dashboard.
Admin / member / viewer role-based access with per-workspace isolation. Single-user setups are unaffected — no login required for solo use.
Personal, shared, and global memory boundaries within the same runtime. Namespaces can have independent mode configurations for different projects.
GDPR Art. 15/17/20 controls (access, erasure, portability), a hash-chained audit trail, and opt-in PII redaction. A per-mode EU AI Act self-assessment ships with the tool — a technical-control map, not a legal certification.
Four integration surfaces — Model Context Protocol, structured CLI, event hooks, and the multi-agent dashboard — without reconfiguring existing workflows.
Four public preprints with protocol-scoped LoCoMo evidence and architecture documentation. See Research →
Published V3 results carried into V4 with original protocol scope. Not a fresh V4 rerun and not an ordinal ranking against Zep claims.
10 conversations / 1,276 questions. Local embeddings, local retrieval. No LLM answer construction.
10 conversations / 1,276 questions. Local retrieval with GPT-4.1-mini answer synthesis disclosed.
Conv-30 only / 81 questions. text-embedding-3-large plus GPT-4.1-mini generation and judge.
Published V3 architecture evidence carried into V4. Mode A covers 10 conversations and 1,276 questions; the 74.8% retrieval result discloses GPT-4.1-mini answer synthesis. Mode C covers Conv-30 only (81 questions) with cloud embeddings and GPT-4.1-mini. Scope differences between Mode A and Mode C make direct ordinal comparison unreliable. LoCoMo protocols are not comparable without matching dataset, answerer, judge, prompts, and context budget.
SuperLocalMemory ships a per-mode EU AI Act self-assessment. It is a technical-control map, not a legal certification — applicability depends on your deployment, data, and operator role.
Regardless of mode: GDPR access / erasure / portability (Art. 15, 17, 20), a hash-chained audit trail, per-workspace isolation, opt-in PII redaction, and admin / member / viewer role-based access. See Governance & EU AI Act controls →
Open source, AGPL v3. A Qualixar Research Initiative.