> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Llms core

# Cognee Core Documentation

> Foundational docs for getting started, core concepts, setup, guides, examples, and contributor-facing documentation.

See the full overview at [https://docs.cognee.ai/llms.txt](https://docs.cognee.ai/llms.txt).

## Getting Started

* [Introduction](https://docs.cognee.ai/getting-started/introduction.md): Learn how Cognee turns your data into searchable AI memory.
* [Installation](https://docs.cognee.ai/getting-started/installation.md): Install Cognee and configure the basics for your first memory workflow.
* [LLM Quickstart Skill](https://docs.cognee.ai/getting-started/llm-quickstart-skill.md): Copy a Claude-ready skill to help an LLM set up Cognee.
* [Python Quickstart](https://docs.cognee.ai/getting-started/quickstart.md): Run your first Cognee workflow with remember and recall.
* [Docs for LLMs](https://docs.cognee.ai/getting-started/docs-for-llms.md): Machine-readable exports of these docs for agents, LLMs, and RAG pipelines.

## Core Concepts

* [Core Concepts Overview](https://docs.cognee.ai/core-concepts/overview.md): Learn the core concepts behind Cognee memory, retrieval, and pipeline design.
* [Architecture](https://docs.cognee.ai/core-concepts/architecture.md): Learn how Cognee combines relational, vector, and graph storage.
* [Data Flows](https://docs.cognee.ai/core-concepts/data-flows.md): Follow the three data pipelines that move memory through Cognee.
* [DataPoints](https://docs.cognee.ai/core-concepts/building-blocks/datapoints.md): Atomic units of knowledge in Cognee.
* [Tasks](https://docs.cognee.ai/core-concepts/building-blocks/tasks.md): Building blocks that transform data in Cognee pipelines.
* [Pipelines](https://docs.cognee.ai/core-concepts/building-blocks/pipelines.md): Orchestrate tasks into coordinated data processing workflows.
* [PipelineContext](https://docs.cognee.ai/core-concepts/building-blocks/pipeline-context.md): Typed runtime context automatically injected into pipeline task functions.
* [Remember](https://docs.cognee.ai/core-concepts/main-operations/remember.md): Store data in Cognee as permanent graph memory or session memory.
* [Recall](https://docs.cognee.ai/core-concepts/main-operations/recall.md): Query Cognee memory with auto-routing and session-aware retrieval.
* [Improve](https://docs.cognee.ai/core-concepts/main-operations/improve.md): Enrich an existing Cognee graph and bridge session memory into it.
* [Forget](https://docs.cognee.ai/core-concepts/main-operations/forget.md): Delete data, datasets, or memory-only state with forget.
* [Serve](https://docs.cognee.ai/core-concepts/main-operations/serve.md): Connect the Cognee SDK to Cognee Cloud or a remote Cognee instance.
* [Push](https://docs.cognee.ai/core-concepts/main-operations/push.md): Upload a local Cognee knowledge graph to a remote Cognee instance.
* [Add](https://docs.cognee.ai/core-concepts/main-operations/legacy-operations/add.md): Ingest and prepare data for processing in Cognee.
* [Cognify](https://docs.cognee.ai/core-concepts/main-operations/legacy-operations/cognify.md): Transform ingested data into a knowledge graph.
* [Search](https://docs.cognee.ai/core-concepts/main-operations/legacy-operations/search.md): Query your AI memory with vectors, graphs, and LLMs.
* [Memify](https://docs.cognee.ai/core-concepts/main-operations/legacy-operations/memify.md): Enrich a knowledge graph with derived knowledge.
* [Delete](https://docs.cognee.ai/core-concepts/main-operations/legacy-operations/delete.md): Remove data from your knowledge graph.
* [Datasets](https://docs.cognee.ai/core-concepts/further-concepts/datasets.md): Organize documents, permissions, and processing with datasets.
* [NodeSets](https://docs.cognee.ai/core-concepts/further-concepts/node-sets.md): Tag and group data in Cognee with NodeSets.
* [Ontologies](https://docs.cognee.ai/core-concepts/further-concepts/ontologies.md): Enrich your knowledge graph with external vocabularies.
* [Global Context Index](https://docs.cognee.ai/core-concepts/further-concepts/global-context-index.md): Build dataset-level summaries to improve graph completion retrieval.
* [Agent Memory Decorator](https://docs.cognee.ai/core-concepts/further-concepts/agent-memory-decorator.md): Attach Cognee memory retrieval to an async agent function.
* [Sessions and Caching](https://docs.cognee.ai/core-concepts/sessions-and-caching.md): Learn how Cognee handles short-term memory with sessions and caching.
* [User Preferences](https://docs.cognee.ai/core-concepts/further-concepts/user-preferences.md): How per-user preference personalization stores ratings and nudges retrieval ranking.
* [Loaders](https://docs.cognee.ai/core-concepts/further-concepts/loaders.md): Learn how Cognee handles different file formats.
* [Chunkers](https://docs.cognee.ai/core-concepts/further-concepts/chunkers.md): Learn how Cognee splits documents into smaller pieces.
* [COGX Exchange Format](https://docs.cognee.ai/core-concepts/further-concepts/cogx.md): The portable format Cognee uses to import memories from other tools and to export, back up, and move its own.
* [Multi-User Mode Overview](https://docs.cognee.ai/core-concepts/multi-user-mode/multi-user-mode-overview.md): Learn how Cognee handles multiple users and data isolation.
* [Dataset Database Handlers: What are they?](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/dataset-database-handlers-what-are-they.md): Learn how Cognee maps datasets to graph and vector storage backends.
* [Dataset Database Handlers: How to use them?](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/dataset-database-handlers-how-to-use-them.md): Learn how to use Dataset Database Handlers in Cognee multi-user mode.
* [Kuzu Dataset Database Handler](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/existing-dataset-database-handlers/kuzu.md): Handler for using Kuzu in Cognee multi-user mode.
* [LanceDB Dataset Database Handler](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/existing-dataset-database-handlers/lancedb.md): Handler for using LanceDB in Cognee multi-user mode.
* [PGVector Dataset Database Handler](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/existing-dataset-database-handlers/pgvector.md): Handler for using PGVector in Cognee multi-user mode.
* [FalkorDB Dataset Database Handler](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/existing-dataset-database-handlers/falkor.md): Handler for using FalkorDB in Cognee multi-user mode.
* [Neo4j Aura Dataset Database Handler](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/existing-dataset-database-handlers/neo4j-aura-dev.md): Handler for using Neo4j Aura in Cognee multi-user mode.
* [Neo4j Community Dataset Database Handler](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/existing-dataset-database-handlers/neo4j-community.md): Handler for per-dataset isolation on Neo4j Community edition using one Docker container per dataset.
* [Qdrant Dataset Database Handler](https://docs.cognee.ai/core-concepts/multi-user-mode/dataset-database-handlers/existing-dataset-database-handlers/qdrant.md): Handler for using Qdrant in Cognee multi-user mode.
* [Permissions System Overview](https://docs.cognee.ai/core-concepts/multi-user-mode/permissions-system/overview.md): Introduction to Cognee's permission system and access control architecture.
* [Datasets in the Permissions System](https://docs.cognee.ai/core-concepts/multi-user-mode/permissions-system/datasets.md): The core unit of data in Cognee's permission system.
* [Principals](https://docs.cognee.ai/core-concepts/multi-user-mode/permissions-system/principals.md): The unified abstraction for entities that can hold permissions in Cognee.
* [Users](https://docs.cognee.ai/core-concepts/multi-user-mode/permissions-system/users.md): Individual users and authentication in Cognee's permission system.
* [Tenants](https://docs.cognee.ai/core-concepts/multi-user-mode/permissions-system/tenants.md): Organization-level access control and permission inheritance in Cognee.
* [Roles](https://docs.cognee.ai/core-concepts/multi-user-mode/permissions-system/roles.md): Role-based permissions within tenants for granular access control.
* [ACL](https://docs.cognee.ai/core-concepts/multi-user-mode/permissions-system/acl.md): Access control lists for permission storage and inheritance in Cognee.

## Setup & Configuration

* [Setup Configuration](https://docs.cognee.ai/setup-configuration/overview.md): Configure Cognee to use your preferred LLM, embedding engine, and storage backends
* [LLM Providers](https://docs.cognee.ai/setup-configuration/llm-providers.md): Configure LLM providers for text generation and reasoning in Cognee
* [Structured Output Backends](https://docs.cognee.ai/setup-configuration/structured-output-backends.md): Configure structured output frameworks for reliable data extraction in Cognee
* [Embedding Providers](https://docs.cognee.ai/setup-configuration/embedding-providers.md): Configure embedding providers for semantic search in Cognee
* [Relational Databases](https://docs.cognee.ai/setup-configuration/relational-databases.md): Configure relational databases for metadata and state storage in Cognee
* [Vector Stores](https://docs.cognee.ai/setup-configuration/vector-stores.md): Configure vector databases for embedding storage and semantic search in Cognee
* [Graph Stores](https://docs.cognee.ai/setup-configuration/graph-stores.md): Configure graph databases for knowledge graph storage and relationship reasoning in Cognee
* [Permissions Setup](https://docs.cognee.ai/setup-configuration/permissions.md): Configure Cognee's permission system and access control
* [Security & Privacy](https://docs.cognee.ai/setup-configuration/security.md): Protect sensitive data and access in self-hosted Cognee deployments.
* [Logging](https://docs.cognee.ai/setup-configuration/logging.md): Control Cognee logging and troubleshoot issues with logs.
* [Adapters Overview](https://docs.cognee.ai/setup-configuration/community-maintained/overview.md): Adapters and extensions built by the Cognee community
* [Qdrant](https://docs.cognee.ai/setup-configuration/community-maintained/qdrant.md): Use Qdrant as a vector store through a community-maintained adapter
* [Redis](https://docs.cognee.ai/setup-configuration/community-maintained/redis.md): Use Redis as a vector store through a community-maintained adapter
* [FalkorDB](https://docs.cognee.ai/setup-configuration/community-maintained/falkordb.md): Use FalkorDB as a hybrid graph and vector store in Cognee.
* [Memgraph](https://docs.cognee.ai/setup-configuration/community-maintained/memgraph.md): Use Memgraph as a graph store through a community-maintained adapter
* [Pinecone](https://docs.cognee.ai/setup-configuration/community-maintained/pinecone.md): Use Pinecone as a vector store through a community-maintained adapter
* [Turbopuffer](https://docs.cognee.ai/setup-configuration/community-maintained/turbopuffer.md): Use Turbopuffer as a vector store through a community-maintained adapter

## Guides

* [Permission Snippets](https://docs.cognee.ai/guides/permission-snippets.md): Practical code snippets and scenarios for Cognee's permission system
* [Remember and Recall in One Script](https://docs.cognee.ai/guides/simple-cognee.md): Store a single passage with remember() and query it back with recall() in the smallest complete Cognee script
* [Search Basics](https://docs.cognee.ai/guides/search-basics.md): Step-by-step guide to running your first Cognee search and understanding core parameters
* [Agent Memory Quickstart](https://docs.cognee.ai/guides/agent-memory-quickstart.md): Minimal end-to-end example showing session memory and graph memory with cognee.agent\_memory
* [Understand Recall with RAG Completion](https://docs.cognee.ai/guides/rag-recall.md): Explore the RAG retrieval workflow with cognee.recall() and learn how its main parameters affect the results
* [Inspecting Graph Completion Context](https://docs.cognee.ai/guides/graph-completion.md): See how GRAPH\_COMPLETION turns retrieved graph triplets into an answer's context, and what a memory fragment is
* [Inspecting Hybrid Retrieval Context](https://docs.cognee.ai/guides/hybrid-retrieval-recall.md): See exactly what HYBRID\_COMPLETION sends to the completion step, and shape it with retriever\_specific\_config
* [Building the Global Context Index](https://docs.cognee.ai/guides/global-context-index.md): See how improve(build\_global\_context\_index=True) builds a dataset-wide summary hierarchy, and how it extends that hierarchy incrementally as new data arrives
* [Reading the Global Context Index](https://docs.cognee.ai/guides/global-context-index-recall.md): See exactly what include\_global\_context\_index adds to GRAPH\_COMPLETION retrieval
* [Time Awareness](https://docs.cognee.ai/guides/time-awareness.md): Step-by-step guide to using temporal mode for time-aware queries
* [Fact Validity](https://docs.cognee.ai/guides/fact-validity.md): Close superseded facts with close\_node() and filter stale ones with is\_valid()
* [Sessions](https://docs.cognee.ai/guides/sessions.md): Step-by-step guide to using sessions for conversational memory in Cognee
* [Session Distillation](https://docs.cognee.ai/guides/session-distillation.md): Turn guidance stated in a session into permanent lessons in the knowledge graph so future recalls respect it
* [Agent Session Traces](https://docs.cognee.ai/guides/agent-session-traces.md): Record what a decorated function did on each call, and recall those traces later
* [Feedback System](https://docs.cognee.ai/guides/feedback-system.md): Step-by-step guide to using feedback with Cognee sessions
* [Web URL Ingestion](https://docs.cognee.ai/guides/web-url-ingestion.md): Step-by-step guide to ingesting web page content with custom extraction rules
* [Folder Presort](https://docs.cognee.ai/guides/presort-downloads.md): Scan a messy folder for junk, duplicates, and personal data before ingesting it as datasets
* [Image OCR Extraction](https://docs.cognee.ai/guides/image-ocr-extraction.md): Print the text an image becomes before you ingest it: the vision-model transcription plus appended OCR text
* [Multilingual Ingestion](https://docs.cognee.ai/guides/multilingual-ingestion.md): Translate non-English content before building the knowledge graph
* [Multimedia Processing](https://docs.cognee.ai/guides/multimedia-audio-image-processing.md): Build a knowledge graph from audio and image files and query their summaries
* [Code Graph](https://docs.cognee.ai/guides/code-graph.md): Build a knowledge graph of a code repository with enola and query it with SearchType.CODE
* [Ontology Quickstart](https://docs.cognee.ai/guides/ontology-support.md): Step-by-step guide to using OWL ontologies to ground Cognee knowledge graphs
* [NodeSet Grouping](https://docs.cognee.ai/guides/nodeset-grouping.md): Tag each memory with node sets so one graph keeps several overlapping topics apart
* [Reading the Visualization](https://docs.cognee.ai/guides/reading-the-visualization.md): What each tab of a rendered graph shows, and which one to reach for
* [Graph Visualization](https://docs.cognee.ai/guides/graph-visualization.md): Step-by-step guide to rendering interactive knowledge graphs
* [Schema Inventory](https://docs.cognee.ai/guides/schema-inventory.md): Summarize your knowledge graph by semantic type with per-type counts, samples, and relationships
* [Memory Provenance](https://docs.cognee.ai/guides/memory-provenance.md): Visualize the ownership and data-flow story behind your memory — tenants, users, agents, datasets, and files
* [Self-Improvement Quickstart](https://docs.cognee.ai/guides/self-improvement-quickstart.md): Step-by-step guide to enriching memory and bridging session content with improve
* [Truth-Subspace Reranking](https://docs.cognee.ai/guides/truth-subspace-reranking.md): Let finished sessions reshape retrieval ordering by reranking against learned 'truth' directions
* [Triplet Embeddings](https://docs.cognee.ai/guides/memify-triplet-embeddings.md): Index graph triplets as embeddings to enable TRIPLET\_COMPLETION search
* [Session Persistence](https://docs.cognee.ai/guides/memify-session-persistence.md): Persist cached conversation sessions into the knowledge graph
* [Entity Consolidation](https://docs.cognee.ai/guides/memify-entity-consolidation.md): Rewrite fragmented entity descriptions using LLM analysis of graph neighborhoods
* [Entity Deduplication](https://docs.cognee.ai/guides/memify-entity-deduplication.md): Detect near-duplicate entity nodes and merge each group into a single canonical node
* [Local Setup (No API Key)](https://docs.cognee.ai/guides/local-setup.md): Run Cognee locally with Ollama and Fastembed.
* [Local Ollama Pipeline](https://docs.cognee.ai/guides/local-ollama.md): Run remember and recall end to end against a local Ollama server and cognee's embedded stores.
* [Recall Without an LLM Key](https://docs.cognee.ai/guides/no-llm-remember-recall.md): Run remember and recall end to end with local GLiNER extraction and fastembed embeddings, with no LLM API key configured at all.
* [Store Configurations](https://docs.cognee.ai/guides/store-configurations.md): Copy-paste .env blocks for the supported relational, vector, and graph store combinations, and how to pair any of them with your LLM and embedding provider.
* [S3 Storage](https://docs.cognee.ai/guides/s3-storage.md): Step-by-step guide to using S3 for data ingestion and storage
* [Neptune Analytics](https://docs.cognee.ai/guides/neptune-analytics.md): Store your knowledge graph and its embeddings in Amazon Neptune Analytics and search them with recall
* [Deploy REST API Server](https://docs.cognee.ai/guides/deploy-rest-api-server.md): Deploy Cognee as a REST API server using Docker or Python
* [Custom Data Models](https://docs.cognee.ai/guides/custom-data-models.md): Step-by-step guide to creating custom data models and using add\_data\_points
* [Custom Graph Model](https://docs.cognee.ai/guides/custom-graph-model.md): Step-by-step guide to creating custom graph models and using remember with them
* [Graph Model from JSON](https://docs.cognee.ai/guides/graph-model-from-json.md): Declare a custom graph model as plain JSON and compile it into a DataPoint model
* [BaseRetriever Guide](https://docs.cognee.ai/guides/base-retriever.md): Learn how BaseRetriever's interface works by building a tiny, fully offline retriever
* [Graph Engine and Adapters](https://docs.cognee.ai/guides/graph-engine-adapters.md): Learn how GraphDBInterface, get\_graph\_engine(), and concrete adapters fit together through a small, offline Ladybug example
* [Custom Tasks and Pipelines](https://docs.cognee.ai/guides/custom-tasks-pipelines.md): Step-by-step guide to creating custom tasks and pipelines
* [Custom GLiNER Extraction](https://docs.cognee.ai/guides/gliner-llm-free-cognify.md): Drive the GLiNER task list yourself to pass your own entity and relation labels and measure what extraction kept
* [Custom Prompts](https://docs.cognee.ai/guides/custom-prompts.md): Step-by-step guide to using custom prompts to control graph extraction
* [Low-Level LLM](https://docs.cognee.ai/guides/low-level-llm.md): Step-by-step guide to using acreate\_structured\_output for direct LLM interaction

## How-To Guides

* [Deployment Overview](https://docs.cognee.ai/how-to-guides/cognee-sdk/deployment.md): Deploy Cognee with flexible data storage options for any scale
* [Deployment Options](https://docs.cognee.ai/how-to-guides/cognee-sdk/deployment/deployment-options.md): Choose a Cognee deployment pattern based on writer ownership, storage, and read scaling
* [Docker Deployment](https://docs.cognee.ai/how-to-guides/cognee-sdk/deployment/docker.md): Deploy Cognee and its supporting services using Docker Compose profiles
* [Docker Compose Reference](https://docs.cognee.ai/how-to-guides/cognee-sdk/deployment/docker-compose-reference.md): Annotated walkthrough of every service, port, and profile in the shipped docker-compose.yml
* [Deploy Cognee on Coolify](https://docs.cognee.ai/how-to-guides/cognee-sdk/deployment/coolify.md): Self-host the Cognee API on your own server with Coolify, an open-source PaaS, using Cognee's Docker Compose stack — from local to online.
* [EC2 Deployment](https://docs.cognee.ai/how-to-guides/cognee-sdk/deployment/ec2.md): Deploy Cognee on Amazon EC2 for traditional cloud server deployments with custom configurations
* [Kubernetes (Helm)](https://docs.cognee.ai/how-to-guides/cognee-sdk/deployment/helm.md): Deploy Cognee on Kubernetes with the in-repo Helm chart for enterprise-grade, production-ready deployments

## Examples

* [Cognee examples overview](https://docs.cognee.ai/examples/overview.md): Browse Cognee examples by use case and pattern.
* [What you can build with Cognee](https://docs.cognee.ai/examples/what-you-can-build.md): Concrete ways teams put Cognee to work.
* [Vertical AI Agents](https://docs.cognee.ai/examples/vertical-ai-agents.md): Use Cognee as the memory layer for vertical AI agents.
* [Data Silos](https://docs.cognee.ai/examples/data-silos.md): Unify siloed enterprise data in a single Cognee memory layer.
* [Edge AI](https://docs.cognee.ai/examples/edge-ai.md): Run Cognee memory pipelines on edge devices with cognee-RS.
* [Developer Knowledge Base](https://docs.cognee.ai/examples/developer-knowledge-base.md): Turn an engineer's profile, past copilot conversations, and a coding-principles document into one memory you can question across all three
* [Company Brain for Docs, Code, and Conversations](https://docs.cognee.ai/examples/company-brain.md): Teach one memory a written fact, a code repository, and a rule stated in conversation, then answer one question that needs all three at once
* [Agentic Procurement Decisions](https://docs.cognee.ai/examples/agentic-procurement.md): Build an agent that researches vendor conversations, purchase history, and policy in separate memory categories, then recommends a vendor with evidence
* [Organizing Your Data](https://docs.cognee.ai/examples/organizing-your-data.md): Ingest the same mixed corpus three ways — one pile, node sets, separate datasets — and watch how each layout changes what recall answers
* [Watch a Session Become Permanent Memory](https://docs.cognee.ai/examples/memory-loop-walkthrough.md): Follow a narrated run in which conversation rules and lessons are absorbed turn by turn, distilled into the knowledge graph, and answered back from a brand-new session
* [Teach an Agent From Its Own Tool Traces](https://docs.cognee.ai/examples/agent-trace-lessons.md): Turn an agent's tool-call successes and failures into agent-profile session guidance, distill it into the knowledge graph, and read it back before the next run
* [Learn a User's Preferences From Conversation Alone](https://docs.cognee.ai/examples/live-session-feedback.md): Run a ten-turn consulting conversation in which stated preferences, corrections, and style rules become session guidance without anyone calling a feedback API
* [Watch Feedback Reshape the Graph](https://docs.cognee.ai/examples/feedback-loop-app.md): Run a local chat app where every answer can be rated and a memify pass turns those ratings into feedback weights you can see move on the graph
* [Resolve Conflicting Facts in Memory](https://docs.cognee.ai/examples/contradiction-handling.md): Feed cognee two documents that disagree and watch it flag the conflict, resist a five-star rating, and change its answer only when a correction is remembered
* [Tune How Strongly Ratings Steer an Answer](https://docs.cognee.ai/examples/feedback-score-shifting.md): Rate one answer up and another down, bake both into graph feedback weights, then sweep feedback\_influence from 0.0 to 1.0 over one ambiguous question and watch the ranking move
* [Let an Agent Rewrite Its Own Weak Skill](https://docs.cognee.ai/examples/self-improving-skills.md): Ingest three SKILL.md playbooks, run them against a real diff, score the one that does the wrong job, and apply the proposal that rewrites its instructions
* [Rebuild Add and Cognify by Hand](https://docs.cognee.ai/examples/rebuild-cognify-pipeline.md): Reproduce cognee's built-in add and cognify stages as custom pipelines, so you can see and change every task they run
* [Typed Claim Extraction](https://docs.cognee.ai/examples/typed-extraction-pipeline.md): Build a three-step custom pipeline that turns a paragraph of research text into typed Person and ScientificClaim nodes, each claim attributed to the person who made it
* [HR Resume Screening](https://docs.cognee.ai/examples/hr-resume-screening.md): Turn a pile of CVs into a queryable candidate graph, then ask who has a given skill — rebuilding the graph only when the corpus changes
* [Mine Coding Rules From Team Chat](https://docs.cognee.ai/examples/coding-rule-mining.md): Turn overlapping team conversations about code standards into deduplicated Rule nodes a coding agent can query before it writes code
* [Org Chart from JSON Exports](https://docs.cognee.ai/examples/org-chart-from-json.md): Turn two flat JSON exports of companies and people into a connected org-chart graph, with deterministic node IDs doing the deduplication
* [Sharing Memory Across Users and Teams](https://docs.cognee.ai/examples/multi-tenant-access-control.md): Give every user their own dataset, then open one up — first to a single colleague with an ACL grant, then to an entire role inside a tenant
* [Migrate Memory Systems with COGX](https://docs.cognee.ai/examples/migrate-memory-systems.md): Import memories from Mem0, LangMem, Letta, Zep, Graphiti, or another Cognee instance using the COGX exchange format.
* [Migrate a Relational Database into a Knowledge Graph](https://docs.cognee.ai/examples/relational-db-migration.md): Convert a relational database schema and data into a searchable knowledge graph

## Cognee CLI

* [Cognee CLI](https://docs.cognee.ai/cognee-cli/overview.md): Command line interface for Cognee AI memory operations

## Contributing

* [Contributing](https://docs.cognee.ai/contributing/contributing-overview.md): Contribute to the cognee project

## Additional Docs

* [Changelog](https://docs.cognee.ai/changelog.md): Recent Cognee releases
* [Rust (Cognee-RS)](https://docs.cognee.ai/rust/getting-started.md): Build on-device AI memory pipelines in Rust with the cognee-cli binary.
* [Core Concepts](https://docs.cognee.ai/rust/concepts.md): The vocabulary behind cognee-rust: the stores that hold memory, the building blocks that produce it, and the terms shared across the API, CLI, and config.
* [Operations](https://docs.cognee.ai/rust/operations.md): What cognee-rust does: the remember / recall / improve / forget memory API and the underlying add / cognify / memify / search pipeline.
* [Configuration](https://docs.cognee.ai/rust/configuration.md): Reference for configuring cognee-rust: how settings resolve and the env vars, defaults, and runtime API for every subsystem.
* [Rust SDK Architecture](https://docs.cognee.ai/rust/architecture.md): The single source of truth for the cognee-rust workspace layout, crate breakdown, cross-cutting design patterns, and key dependencies.
* [Guides](https://docs.cognee.ai/rust/guides/overview.md): Task-oriented how-tos for cognee-rust, each with what the feature does, when to use it, a runnable example, and a pointer into the code.
* [Custom Graph Schema](https://docs.cognee.ai/rust/guides/custom-graph-schema.md): Swap the LLM's structured output shape in cognify via summarization\_model (wired) and graph\_model (set but not consumed in the standalone pipeline).
* [Rust SDK Custom Prompts](https://docs.cognee.ai/rust/guides/custom-prompts.md): Override the LLM prompt the cognify pipeline uses for entity/relationship (graph) extraction via the CognifyConfig builder.
* [Memify Node Filtering](https://docs.cognee.ai/rust/guides/memify-node-filtering.md): Scope memify enrichment to a specific node set — a node type plus one or more node names — from the CLI or programmatically.
* [Ontology](https://docs.cognee.ai/rust/guides/ontology.md): Ground cognify extraction against an RDF/OWL, Turtle, or JSON-LD ontology so entities are matched to a known vocabulary.
* [Temporal Cognify](https://docs.cognee.ai/rust/guides/temporal-cognify.md): Run the temporal cognify variant to extract events and timestamps, then query them with the TEMPORAL search type or recall.
* [Tools Overview](https://docs.cognee.ai/rust/tools/overview.md): The ways to drive cognee-rust, the backends it runs on, and the supporting dev/ops tooling.
* [CLI Reference](https://docs.cognee.ai/rust/tools/cli.md): The cognee-cli command-line binary: subcommands, flags, config, retries, and logging.
* [Language Bindings](https://docs.cognee.ai/rust/tools/bindings.md): Python, C, and JavaScript SDKs for cognee-rust, built on a shared bindings-common core.
* [Pluggable Backends](https://docs.cognee.ai/rust/tools/backends.md): Swap cognee-rust storage and compute backends (LLM, embeddings, vector, graph, relational, storage, session, ontology, tokenizer) via configuration.
* [HTTP Server (Tools)](https://docs.cognee.ai/rust/tools/http-server.md): Launch the cognee-http-server binary or embed it as a library; an axum server exposing the FastAPI surface under /api/v1/\*.
* [HTTP Server](https://docs.cognee.ai/rust/http-server.md): Design and reference for cognee-http-server, the axum server mirroring the Python FastAPI surface under /api/v1/\*.
* [TypeScript (@cognee/cognee-ts)](https://docs.cognee.ai/typescript/getting-started.md): Build AI-memory pipelines in Node.js with the @cognee/cognee-ts SDK.
* [Configuration](https://docs.cognee.ai/typescript/configuration.md): Configure the @cognee/cognee-ts SDK through constructor settings, the c.config setters, and environment variables.
* [Memory API](https://docs.cognee.ai/typescript/memory-api.md): The high-level memory operations in @cognee/cognee-ts: remember, recall, improve, forget, and rememberEntry.
* [Resource Managers](https://docs.cognee.ai/typescript/resources.md): Manage datasets, sessions, notebooks, and users through the namespaced managers on a Cognee handle.
* [Legacy Pipeline Operations](https://docs.cognee.ai/typescript/legacy-operations.md): Staged add, cognify, addAndCognify, search, and memify calls for explicit control over the @cognee/cognee-ts pipeline.
* [Maintenance and Visualization](https://docs.cognee.ai/typescript/maintenance.md): Replace or prune stored data and render the knowledge graph to HTML with @cognee/cognee-ts.
* [Cognee Cloud](https://docs.cognee.ai/typescript/cloud.md): Connect a local @cognee/cognee-ts process to Cognee Cloud with the module-level serve and disconnect functions.
* [Runtime and Observability](https://docs.cognee.ai/typescript/runtime.md): Boot and shut down the Rust runtime behind @cognee/cognee-ts, and wire up logging, tracing, and analytics.
* [Low-level Pipeline API](https://docs.cognee.ai/typescript/pipeline-api.md): Build custom task pipelines with the pipeline namespace exported by @cognee/cognee-ts.