Knowledge Graph / GraphRAG

Tool
Category
Segment
Platform / Tool
Plan / License
Monthly Price USD
Pricing Model
Free Tier / OSS
Included Usage / Limits
Graph Construction / Knowledge Model
Retrieval / Reasoning
GraphRAG / Context Features
Integrations / Frameworks
Deployment / Hosting
Security / Privacy
Team / Governance
Best Fit
Main Limits / Caveats
No tagline
Knowledge Graph / GraphRAGProperty-graph retrieval layerLlamaIndex Property Graph IndexMIT$0 softwareOpen-source framework component; model, embedding and graph-store costs separateNo software usage capPropertyGraphIndex extracts graph nodes and relations into a simple in-memory store or external property-graph backendsComposable PGRetriever supports LLM synonyms, vector context, TextToCypher, Cypher templates and custom sub-retrieversGraph construction and retrieval can be combined with the broader LlamaIndex ingestion, query-engine and agent ecosystemPython, LlamaIndex, Neo4j and other property-graph stores plus configurable LLM/embedding providersEmbedded/local or customer-managed infrastructureSecurity and data handling depend on the selected graph store and model providersNo independent hosted governance in the OSS index layerExisting LlamaIndex applications that need property-graph extraction and modular retrieversThis is a component of a broader framework, not a turnkey GraphRAG product; quality depends on extraction prompts and graph schema
No tagline
Knowledge Graph / GraphRAGLightweight GraphRAG frameworkLightRAGMIT$0 softwareOpen-source server/core; model, embedding, reranker and storage costs separateNo software usage cap; REST server, Web UI and local core are includedBuilds an entity-relation knowledge graph linked to chunks, vectors, document status and LLM response cachesLocal, global, hybrid, mix and naive query modes; optional reranker and graph-plus-vector retrievalIncremental ingestion, entity and relation management, deletion/merge, citations, graph export, evaluation and observability hooksOpenAI, Azure, Gemini, Ollama, Hugging Face and LlamaIndex providers; NetworkX, Neo4j, PostgreSQL AGE, Memgraph, MongoDB and Redis storage optionsSelf-hosted Python, REST server, Docker or KubernetesCan run fully local; external model and storage services determine the final data pathNo hosted RBAC in OSS; operational controls depend on the chosen deployment stackTeams wanting a practical self-hosted GraphRAG server with multiple storage and model backendsRequires coordinated KV, vector, graph and document-status storage; embedding model changes can require rebuilding data
No tagline
Knowledge Graph / GraphRAGManaged temporal context graphZepCommercial cloud SaaS$0Credit-based cloud pricing; paid Flex starts at $125/month1,000 credits/month, 2 projects, 5 custom entity/edge types and variable rate limits; free credits do not roll overManaged temporal context graphs ingest messages, JSON and text into evolving entities, facts and relationshipsLow-latency relationship-aware retrieval with incremental updates and temporal fact validityManaged users, threads, context assembly, API logs, graph visualization and production SDKsPython, TypeScript and Go SDKs plus common agent frameworksManaged cloud; Enterprise supports BYOK, BYOM and BYOC in AWSSOC 2 Type II; HIPAA BAA, audit logs and stronger residency controls are Enterprise featuresFree includes 2 projects; Flex includes 5 projects; Enterprise adds SLA, support and governanceProduction agents that need managed real-time GraphRAG and temporal memoryCredits are based on episode size; free rate limits are variable and Graphiti flexibility is reduced in exchange for managed behavior
No tagline
Knowledge Graph / GraphRAGGraphRAG frameworkMicrosoft GraphRAGMIT$0 softwareOpen-source framework; LLM, embedding, storage and compute costs separateNo software usage cap; current repository warns that indexing can be expensiveLLM extraction of entities, relationships and claims, followed by community detection and community reports over a document corpusLocal, global and graph-aware search modes assemble evidence from entities, relationships, communities and source textCLI and Python pipeline, prompt tuning, structured artifacts and a unified search applicationPython, OpenAI/Azure-oriented model configuration, Parquet artifacts and custom data pipelinesLocal or customer-managed infrastructureData path is controlled by the selected model and storage providers; no Microsoft-hosted service is includedSource-control governance only; repository states the code is a demonstration and not an officially supported Microsoft offeringCorpus-wide thematic discovery and multi-hop questions over large private text collectionsIndexing cost can be high; configuration changes across versions may require migration or re-indexing
No tagline
Knowledge Graph / GraphRAGMinimal GraphRAG implementationnano-graphragMIT$0 softwareOpen-source Python library; model and storage costs separateNo software usage cap; package is roughly 1,100 lines excluding tests and promptsExtracts graph entities and communities from text with compact local persistence and optional Neo4j/FAISS componentsLocal and global GraphRAG search plus optional naive RAG; async APIs and incremental insert are supportedSmall typed codebase intended for inspection, modification and experimentationPython, OpenAI/Azure, Ollama, FAISS and Neo4j-oriented extensionsLocal/customer infrastructureCan stay local with local models and stores; external APIs change the data pathNo team control plane or managed governanceResearchers and developers who need a compact, hackable GraphRAG reference implementationDoes not implement every Microsoft GraphRAG feature; community reports are recomputed after inserts and production hardening is limited
No tagline
Knowledge Graph / GraphRAGMultimodal GraphRAG frameworkRAG-AnythingMIT$0 softwareOpen-source framework; parsing, vision, LLM, embedding and storage costs separateNo software usage capBuilds a multimodal knowledge graph from text, images, tables, equations and document hierarchyFuses vector similarity with graph traversal and modality-aware rankingEnd-to-end document parsing, cross-modal relationships, hierarchy preservation and multimodal query answeringPython, LightRAG, MinerU and configurable vision/LLM/embedding providersSelf-hosted application or serviceLocal deployment is possible, but OCR, vision and model services may receive document contentNo built-in enterprise governance in the OSS projectComplex PDF, Office and multimodal knowledge bases where relationships cross text, images and tablesMore dependencies and processing stages than text-only GraphRAG; parser and model quality strongly affect the graph
No tagline
Knowledge Graph / GraphRAGSemantic context graph platformTrustGraphApache-2.0$0 softwareOpen-source full stack; model, storage and infrastructure costs separateNo software usage capBuilds context graphs using RDF/OWL-oriented semantics, ontologies, schemas and governed document ingestionGraphRAG queries expose provenance and explainability; graph neighborhoods and semantic workflows support agent contextAgent console, GraphRAG view, 3D context explorer, ontology workbench, schema tools, flows and prompt editingPython services, TypeScript UI clients, SPARQL/RDF/OWL/SHACL ecosystem and configurable model infrastructureContainerized deployment through Docker, Podman, Minikube or KubernetesDesigned for private sovereign deployments with customer control of models and dataWorkspace management and workbench tools are included; identity/RBAC depth depends on the deployed configurationOrganizations needing an explainable, ontology-heavy GraphRAG platform rather than a small libraryLarge multi-service platform with more operational complexity than embedded retrieval SDKs
No tagline
Knowledge Graph / GraphRAGGraph memory platformCogneeApache-2.0 OSS; commercial cloud$35/month cloud; $0 OSSOpen-source self-hosting or fixed managed plans with data/document top-upsDeveloper includes 1 user, 1,000 documents or 1 GB and 10,000 API calls; OSS has no software cap; 14-day cloud trial is documentedCognify pipelines combine embeddings, entities, relationships, ontologies, provenance and feedback into graph memoryRecall auto-routes across session memory, semantic search and graph-connected knowledgeRemember/recall/forget/improve API, multimodal ingestion, evaluations, MCP, UI and agent memory pluginsPython, MCP, Claude Code, LangGraph, OpenClaw, Kuzu, LanceDB, PostgreSQL and many data sourcesLocal/self-hosted, Cognee Cloud, Modal, Railway, Fly.io, Render or enterprise on-premSelf-hosting supports air-gapped control; cloud provides permissions, RBAC and audit-oriented featuresDeveloper is single-user; Team is $200/month for 10 users and multi-tenant memory groupingTeams needing a broad agent-memory layer that blends knowledge graphs and vector retrievalBroader than GraphRAG alone; cloud document/API allowances and top-up pricing must be modeled for production volume
No tagline
Knowledge Graph / GraphRAGGraph retrieval layerDataStax Graph RAGApache-2.0$0 softwareOpen-source retriever library; vector store and model costs separateNo software usage capDoes not build a separate graph database; graph edges are defined through metadata relationships already stored with vectorsCombines vector similarity with traversal of metadata properties to retrieve connected chunksGeneric graph-retriever core and LangChain-specific GraphRetriever wrapperPython, LangChain and supported vector-store adapters including Astra DB patternsEmbedded in customer applicationsData remains in the configured vector store and application/model stackNo hosted governance or control planeAdding relationship traversal to an existing vector-store RAG system without adopting a graph databaseRelationship metadata must already exist; backend support is limited and the last public release listed is April 2025
No tagline
Knowledge Graph / GraphRAGLocal GraphRAG applicationGraphRAG Local UIMIT$0 softwareOpen-source local application; local hardware and optional model API costs separateNo software usage capAdapts Microsoft GraphRAG indexing and prompt tuning for local models and local artifactsSupports global, local and direct chat queries through a FastAPI backendGradio indexing UI, prompt tuning, file management, output exploration and 2D/3D graph visualizationPython, FastAPI, Gradio, Ollama and OpenAI-compatible local endpointsLocal/self-hosted; primarily documented for workstation useCan keep documents and models local; optional external endpoints change the data pathNo multi-user governance; collaborative features remain roadmap itemsDevelopers wanting a visual local GraphRAG workbench around Microsoft GraphRAG conceptsRepository says updates are slow, the UI architecture is transitioning and testing has focused mainly on a Mac Studio M2
No tagline
Knowledge Graph / GraphRAGKnowledge-graph reasoning researchThink-on-GraphApache-2.0 stated in README$0 softwareOpen-source research implementation; KG endpoints and model calls separateNo software usage capOperates on existing large knowledge graphs such as Freebase or Wikidata rather than constructing a document graphIteratively explores candidate relations and entities with LLM-guided pruning to form reasoning pathsResponsible, interpretable graph traversal for multi-hop knowledge-graph question answeringPython, Freebase, Wikidata and configured LLM APIsLocal research environment plus external or local KG serviceQueries and intermediate paths follow the configured KG and LLM servicesNo production team controls or hosted serviceResearchers comparing explicit KG traversal and multi-hop reasoning methodsResearch code and datasets require setup; not a document-ingestion GraphRAG framework or supported production SDK
No tagline
Knowledge Graph / GraphRAGBiomedical KG-RAG frameworkKG-RAGApache-2.0$0 softwareOpen-source biomedical framework; SPOKE access, model and infrastructure costs separateNo software usage capUses the SPOKE biomedical knowledge graph and disease/entity recognition to ground queries in curated relationshipsRetrieves graph neighborhoods and semantically prunes context before LLM generationEvidence-focused biomedical answers with provenance, configurable graph depth and GPT or local Llama workflowsPython, Neo4j/SPOKE, sentence transformers, OpenAI and local Llama examplesLocal/customer infrastructure; a specialized API is also documented by the project teamCan self-host the pipeline; biomedical source licenses and model-provider policies still applyNo general team governance; specialized institutional deployments manage access separatelyBiomedical question answering that can rely on SPOKE concepts and relationshipsDomain-specific rather than general purpose; some releases and examples are older and require external biomedical graph access
No tagline
Knowledge Graph / GraphRAGGraphRAG SDKFalkorDB GraphRAG SDKApache-2.0$0 softwareOpen-source SDK; FalkorDB, model, embedding and hosting costs separateNo software usage capIngests raw documents into configurable entity/relation schemas with entity resolution, deduplication, provenance and incremental updatesCombines vector search, full-text search, Cypher, relationship expansion, optional Text2Cypher and local cosine rerankingCited answers, per-tenant graph names, change application APIs, crash-safe updates and pluggable strategies/providersPython, FalkorDB, LiteLLM and custom LLM/embedder providersSelf-hosted SDK with local or managed FalkorDBData control follows the FalkorDB and model deployment; source provenance is retained through MENTIONS edgesGraph-name isolation supports multi-tenant patterns; broader RBAC depends on the database/deploymentProduction-oriented GraphRAG pipelines that want a focused SDK and FalkorDB performanceRequires FalkorDB and a finalize step whose cross-document deduplication cost grows with graph size
No tagline
Knowledge Graph / GraphRAGGraph memory and multi-hop retrievalHippoRAGMIT$0 softwareOpen-source research package; LLM, embedding and GPU costs separateNo software usage capUses OpenIE outputs to build a graph-like long-term memory connecting passages, entities and factsPersonalized PageRank and graph-based association support multi-hop retrieval, sense-making and continual knowledge integrationSeparate retrieval and QA APIs, incremental updates, deletion, reranking and evaluation workflowsPython, OpenAI/Azure/Bedrock-compatible paths, local vLLM and selected embedding modelsLocal research or customer infrastructureLocal deployment is supported; hosted model providers receive configured prompts and documentsNo hosted team governance or production control planeMulti-hop QA and agent memory research where associative retrieval is more important than corpus summarizationResearch-oriented setup can require GPUs and specific embedding/OpenIE configurations; production operations are user-owned
No tagline
Knowledge Graph / GraphRAGAdaptive GraphRAG frameworkFast GraphRAGMIT$0 software; managed service has 100 free requests/monthOpen-source library or usage-based managed service; public post-free pricing is not itemized in the repositoryNo OSS software cap; first 100 managed requests are free each monthAutomatically generates and refines a domain graph and supports incremental updates as source data changesPersonalized PageRank-based exploration targets relevant graph regions for interpretable retrievalPromptable graph behavior, async typed APIs, dynamic data updates and lower-cost indexing goalsPython, PyPI, OpenAI-compatible models and configurable local infrastructureSelf-hosted library or Circlemind managed serviceSelf-hosting controls the data path; managed-service privacy and residency require a service reviewOSS has no team governance; managed controls are not publicly detailedApplications needing faster incremental graph retrieval without the full Microsoft GraphRAG pipelineManaged pricing after the free allowance is not public; framework maturity and backend choices still need production validation
No tagline
Knowledge Graph / GraphRAGKnowledge-augmented reasoning frameworkKAGApache-2.0$0 softwareOpen-source framework built on OpenSPG; model and infrastructure costs separateNo software usage capCombines schema-free extraction with schema-constrained professional knowledge, semantic alignment and graph-to-chunk mutual indexingLogical-form-guided hybrid reasoning and retrieval supports factual, logical and multi-hop questionsDomain ontology modeling, knowledge construction, reasoning operators and professional knowledge-base workflowsPython, OpenSPG engine, graph/search components and configurable LLM providersSelf-hosted/customer-managedPrivate deployment is possible; model and search backends determine external data exposureGovernance follows the OpenSPG deployment; no standalone hosted team plan is includedProfessional-domain knowledge bases where rules, schemas and multi-hop factual reasoning matterOperationally heavier than lightweight GraphRAG libraries and depends on the OpenSPG ecosystem
No tagline
Knowledge Graph / GraphRAGSmall-model GraphRAG frameworkMiniRAGMIT$0 softwareOpen-source research framework; model, graph store and compute costs separateNo software usage cap; repository reports support for API/Docker and 10+ heterogeneous graph databasesCreates a heterogeneous graph linking text chunks and named entities with a compact indexLightweight topology-enhanced retrieval is designed to work with small and open-source language modelsOn-device-oriented design, included benchmark data and graph visualization componentsPython, LightRAG-derived components, Neo4j, PostgreSQL, TiDB and other graph backendsLocal, API or Docker deploymentCan use local small models and self-hosted graph storageNo hosted collaboration or policy layerResource-constrained and on-device experiments requiring graph retrieval with small modelsEarly project with a small number of releases; production scalability and backend compatibility need validation
No tagline
Knowledge Graph / GraphRAGTemporal context graph frameworkGraphitiApache-2.0$0 softwareOpen-source framework; graph database, model and infrastructure costs separateNo software usage capBuilds temporal context graphs with entities, facts, validity windows, episodes, provenance and custom Pydantic ontologiesHybrid semantic, keyword and graph-traversal search with graph-distance reranking and historical queriesContinuous incremental updates, contradiction handling, temporal history, provenance and MCP/REST optionsPython, Neo4j, FalkorDB, Kuzu, Amazon Neptune, OpenAI, Anthropic, Groq, Gemini, Ollama and LangGraph examplesSelf-hosted only for Graphiti; managed deployment is the separate Zep productRepository says anonymous environment/configuration telemetry is enabled by default but can be disabled; graph content and queries are not collectedNo built-in users, threads, dashboard or enterprise governance in the OSS engineDynamic agent context and memory where facts change over timeRequires an external graph backend and surrounding production tooling; default ingestion can trigger model-provider rate limits
No tagline
Knowledge Graph / GraphRAGGraph retrieval SDKNeo4j GraphRAG for PythonApache-2.0$0 softwareOpen-source Python package; Neo4j hosting, model and embedding costs separateNo package usage capKnowledge Graph Builder pipelines can extract entities and relationships into Neo4j; existing graphs can be used directlyVector, hybrid, graph traversal, Text2Cypher and external-vector-store retrievers feed a common GraphRAG generation pipelineFirst-party Neo4j package with retrievers, LLM/embedder adapters, KG construction and source-aware generationPython, Neo4j, OpenAI, Azure, Gemini, Cohere, Anthropic, Mistral, Bedrock, Ollama, Weaviate, Pinecone and QdrantSelf-hosted Neo4j or Neo4j Aura plus application infrastructureSecurity, encryption, tenancy and residency follow the selected Neo4j deployment and model providersNo separate SaaS governance in the library; Aura and Neo4j Enterprise controls apply to the database layerPython teams standardizing GraphRAG on Neo4j with supported retriever patternsTied to Neo4j for graph operations; some KG Builder components are experimental and ANN vector search is approximate
No tagline
Knowledge Graph / GraphRAGMedical GraphRAG researchMedical Graph RAGMIT$0 softwareOpen-source research system; model, API, dataset and infrastructure costs separateNo software usage capConstructs hierarchical medical graphs linking private patient data, literature/books and dictionary/ontology sources such as UMLSRetrieves evidence across graph levels for grounded medical question answeringAgentic chunking, graph construction, hierarchical linking, PubMed-oriented demo and Docker examplePython, Docker, OpenAI, NCBI/PubMed, UMLS and included GraphRAG componentsLocal research deployment or Docker demoMedical data requires strict local governance; external OpenAI/NCBI calls can expose query or document contentNo clinical access-control or compliance layer is provided by the research codeResearch on evidence-backed medical retrieval across private and public knowledge layersNot a clinical product; source datasets can be licensed/restricted and outputs require medical validation
No tagline
Knowledge Graph / GraphRAGGNN graph retriever researchGNN-RAGNo explicit license detected$0 code; commercial rights unclearPublic research repository; training, KG and inference costs separateCode availableNo software usage capUses a graph neural network retriever over an existing knowledge graph to identify relevant entities, relations and pathsRetrieved graph evidence is supplied to an LLM for knowledge-graph reasoning and QASeparates graph retrieval from language generation and includes research evaluation workflowsPython, PyTorch/graph ML tooling, KGQA datasets and LLM componentsLocal research environmentData remains in the configured research stack unless external model APIs are usedNo team governance or hosted serviceGraph ML researchers testing learned subgraph/path retrieval for LLM reasoningNo explicit repository license was detected, so reuse beyond research needs legal review; setup is benchmark-oriented
No tagline
Knowledge Graph / GraphRAGGraph foundation model retrieverGFM-RAGApache-2.0$0 softwareOpen-source package and pretrained retrievers; compute, model and graph-building costs separateNo software usage capBuilds a graph index from documents or loads a user-provided nodes/relations/edges graph formatA pretrained graph foundation model retrieves relevant documents by reasoning over graph structure and can be fine-tuned on query-document pairsBring-your-own-graph path, reusable G-reasoner models, retrieval API and QA/evaluation workflowsPython, PyPI, Hydra, PyTorch, Hugging Face models and configurable graph constructorsLocal research or customer GPU infrastructureCan operate locally; model downloads and any external LLM generation follow provider policiesNo hosted team governanceTeams researching learned graph retrievers that transfer across unseen datasetsHeavier ML stack than rule-based graph retrieval; GPU and model compatibility need validation for production
No tagline
Knowledge Graph / GraphRAGMarkdown graph retrieval layerIWEApache-2.0$0 softwareOpen-source local CLI/LSP/MCP tool; no model or database service is bundledNo software usage cap; repository reports processing 20,000 files in under a secondTurns Markdown files and links into a local knowledge graph without a vector databaseCLI and MCP tools let agents search, read, navigate and refactor linked notesGit-versioned plain-text knowledge, editor navigation, structured agent access and no built-in AI dependencyRust CLI, MCP, VS Code, Neovim, Zed, Helix, Claude, Codex and GeminiLocal-only/customer filesystemNo cloud, database or vendor lock-in; files remain under user controlGovernance follows filesystem permissions and Git review workflowsDeveloper and research knowledge bases that are already organized as linked MarkdownNot an automatic document-to-KG or answer-generation system; graph quality depends on authored links and note structure
No tagline
Knowledge Graph / GraphRAGOntology-grounded hypergraph RAGOG-RAGMIT$0 softwareOpen-source research implementation; model and infrastructure costs separateNo software usage capMaps domain documents and expert ontologies into hypergraph representations of related factual knowledgeOptimization-based retrieval selects a compact set of hyperedges that covers query-relevant factsOntology grounding, fact-focused context assembly and traceable attribution for specialized workflowsPython, domain ontologies, embeddings and configured LLM servicesLocal/customer research infrastructureCan be self-hosted; model-provider and ontology-source policies determine data handlingNo hosted governance or team workflowHigh-stakes domain workflows where ontology-defined facts and attribution matterRequires a usable domain ontology and mapping process; repository has no packaged releases and remains research-oriented