Knowledge graph / GraphRAG7 frameworks · 3 use cases

Knowledge graph / GraphRAG

Memory as entities and relationships; recall traverses the graph.

Memory is stored as entities and the relationships between them, forming a graph rather than a flat list. Recall traverses the graph, which makes multi-hop questions ('who worked on the project that depended on X?') answerable without re-reading everything. Two distinct sub-shapes live here: bi-temporal graphs where every fact carries validity windows and stale facts auto-supersede ('what's true now + how it changed'), and GraphRAG engines that ingest a large corpus into an ontology-grounded graph and reason over it toward a conclusion.

What makes this family unique

Supersession and multi-hop. No other family can answer 'how did this project's scope drift over the quarter' (that requires validity windows) or 'reason over a corpus that won't fit in one LLM toward a conclusion' (that requires graph traversal). The cost is heavier infrastructure — a graph DB or graph-shaped store — and more setup than extract-retrieve. When the binding constraint is a current truth that drifts, or corpus ingestion plus multi-hop synthesis, this is the only family that fits.

Frameworks in this family

7 catalogued.

Hindsight

Vectorize

18k

Knowledge graph / GraphRAG

'reflect' synthesizes conclusions across all memories; retains full turns including tool calls.

Self-host: moderateFree + paidMIT

Best for: Apps where recall accuracy is the priority (strong LongMemEval scores) · Persistent memory for coding agents (Claude Code / Cursor / OpenCode)

View memory card →

Zep (Graphiti)

Zep / Graphiti

28k

Knowledge graph / GraphRAG

Bi-temporal knowledge graph — every fact carries validity windows; stale facts are auto-superseded.

Self-host: heavyFree + paidApache-2.0

Best for: Facts that change over time

View memory card →

Cognee

Topoteretes

25k

Knowledge graph / GraphRAG

ECL ingestion of 38+ formats into an ontology-grounded graph; 14 retrieval modes.

Self-host: moderateFree + paidApache-2.0*

Best for: Local-first GraphRAG over a large, mixed-format corpus · Edge / on-device memory (Rust engine) · Enterprise knowledge-graph workflows (e.g. research / evidence graphs)

View memory card →

HippoRAG

OSU-NLP-Group

3.8kDormantNeeds review

Knowledge graph / GraphRAG

A neurobiologically inspired long-term memory framework that builds a knowledge graph over documents and retrieves with Personalized PageRank, enabling continual integration of knowledge. HippoRAG 2 improves multi-hop associativity and sense-making.

Self-host: moderateFree / OSSMIT

Best for: Multi-hop retrieval and knowledge integration over large document corpora

View memory card →

Memary

kingjulio8238

2.6kDormantNeeds review

Knowledge graph / GraphRAG

An open-source memory layer for autonomous agents that records agent actions into a knowledge graph you can view, search, and configure.

Self-host: moderateFree / OSSMIT

Best for: Agents that benefit from an inspectable knowledge-graph memory of their actions

View memory card →

LiCoMemory

HKUST & Huawei (research)

47Stale

Knowledge graph / GraphRAG

An end-to-end agentic memory framework built around CogniGraph, a lightweight hierarchical graph that uses entities and relations as semantic indexing layers. Targets efficient long-term reasoning: keep the memory graph small and the retrieval cheap while preserving multi-session recall. Published as an arXiv 2025 paper with public code.

Self-host: moderateFree / OSSunlicensed

Best for: Researchers comparing graph-based agentic memory under a controlled, efficiency-focused evaluation

View memory card →

MemoryBear

RedBear AI (Suanmo Suanyang Technology)

4.7k

Knowledge graph / GraphRAG

Next-generation AI memory system inspired by hippocampal memory encoding and neocortical knowledge consolidation. Spans the full knowledge lifecycle: perception → extraction → association → forgetting. LLM-driven extraction converts conversations into structured entity-relationship triples stored in a Neo4j knowledge graph, while a parallel vector store enables hybrid semantic+keyword retrieval. A biologically-motivated forgetting engine (dormancy → decay → clearance) prunes low-value knowledge automatically.

Self-host: heavyFree + paidApache-2.0

Best for: AI assistants and agents that need rich relational knowledge management — especially where entity relationships, temporal tracing, and automated forgetting matter more than pure vector recall speed

View memory card →

Use cases this family is built for

Top-down recommendations from the use-case playbook. Each names the one binding constraint that picks the tool, the primary pick (which may sit in another family when the case spans more than one), and runner-ups.

Production B2B / customer-support agent at scale

Binding constraint: Multi-tenant isolation + compliance (SOC2/HIPAA) + customer 'current state' (plan, tier, tickets) that changes.

Pick

Supermemory — SOC2/HIPAA (Scale tier), connectors, context fencing, sub-300ms, multi-tenant.

Runner-up

Zep (Graphiti) — If temporal state (a customer's current plan/tickets that drift) is the heart of it.

Hard no: Cognee — no SOC2/HIPAA as of mid-2026, disqualifying for regulated data.

From Agentic Memory: Use-Case Playbook 2026 · last verified 2026-06-28

Project tracking — always-current state, ingest everything, no end date

Binding constraint: Supersession. The hard part isn't storing state, it's making sure last month's status never resurfaces as current.

Pick

Hand-curation is the honest default — you own supersession by editing the living doc yourself.

A curated LLM wiki (Obsidian/PARA-style) is the correct architecture here, because you curate and overwrite the living document. A memory product only wins when one of the runners-up's unique property becomes the pain.

Runner-ups

Zep (Graphiti) — When hand-curation can't keep up: its core feature — validity windows (valid_at/invalid_at) with automatic supersession — IS 'always current state.' It can also answer 'how did this project's scope drift over the quarter,' which a wiki can't unless you wrote that history by hand.
ByteRover — When you want to keep editable markdown but add retrieval: its Domain→Topic→Subtopic tree is wiki-shaped, git-friendly, hand-editable.

Why not Cognee here: it accumulates a corpus but is weaker at 'this new fact replaces that old one.' Supersession is Zep's lane.

From Agentic Memory: Use-Case Playbook 2026 · last verified 2026-06-28

Deep research / time-bounded decision — ingest more than fits in an LLM, reason with HITL

Binding constraint: Corpus ingestion + multi-hop reasoning toward a conclusion.

Pick

Cognee — ECL pipeline ingests 38+ formats into an ontology-grounded graph with 14 retrieval modes including multi-hop — the GraphRAG engine the 'won't fit in one LLM' requirement demands. Pair with Hindsight's reflect to synthesize.

Runner-up

Hindsight — reflect walks all memories to form cross-cutting conclusions and retains full turns including your agent's tool calls, so the research trail is itself queryable. Pick Hindsight alone when the bottleneck is an agentic loop where synthesis and 'what did we already try' dominate.

If you must pick one: Cognee when the bottleneck is ingesting/structuring data; Hindsight when it's an agentic loop. Boundary: for a static document pile needing only grounded Q&A (no ongoing agent), a NotebookLM-style tool is overkill's opposite — a memory product is overkill.

From Agentic Memory: Use-Case Playbook 2026 · last verified 2026-06-28

Last verified 2026-06-28 · updated by manual-stub