Skip to main content

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.

Cognee releases with highlights and links to the full release notes on GitHub.

​
v1.1.1.dev0

View on GitHub Developer preview release after v1.1.0 with API default fixes and backend stability improvements.

​
Highlights

  • Adds ontology_key support to the remember REST endpoint, letting API callers use previously uploaded ontologies during knowledge graph construction.
  • Hardens Postgres-backed graph and PGVector writes for concurrent ingestion, deletion, and dataset-tag updates.
  • Adds statistics percentile benchmark/report tooling for measuring Cognee ingest, cognify, and search performance.

​
Notable Changes

  • Bumps the package version from 1.1.0 to 1.1.1.dev0.
  • Adds a relational migration that changes stored graph node label and type columns from bounded VARCHAR(255) fields to unbounded TEXT fields on non-SQLite databases.
  • Raises the cognee-mcp package’s minimum Cognee dependency to >=1.1.0.

​
Bug Fixes

  • Remember and search API defaults: Optional request fields in the remember, recall, and search routers now expose None/empty defaults more accurately in generated API schemas. The remember endpoint also returns a validation-style 409 response for invalid request data instead of falling through to the generic error handler.
  • LLM rate-limit interval: The client-side LLM rate limiter now uses LLM_RATE_LIMIT_INTERVAL for its window length. It previously read EMBEDDING_RATE_LIMIT_INTERVAL by mistake, so LLM throttling silently followed the embedding interval whenever the two values differed. Deployments that set both variables to the same value (including the 60/60 defaults) see no behavior change; deployments that configured LLM_RATE_LIMIT_INTERVAL separately will now have LLM requests paced against that value after restart.
  • Postgres graph deadlocks on concurrent writes and deletes: The Postgres graph adapter (GRAPH_DATABASE_PROVIDER=postgres) now serializes its node and edge upserts and its delete operations (delete_nodes, delete_graph) through a per-adapter asyncio.Lock, which helps avoid deadlocks observed when multiple coroutines concurrently wrote to or deleted from graph_node/graph_edge in the same process. The PGVector adapter’s deadlock retry also now retries on DBAPIError in addition to DeadlockDetectedError. There are no API or configuration changes for this adapter behavior; heavily concurrent delete/write workloads may see slightly reduced peak adapter-level concurrency within each adapter instance.
  • PGVector concurrent writes and long relational graph labels: PGVector writes, deletes, and dataset-tag cleanup now use per-collection write locks, reducing deadlocks during concurrent vector updates. Stored graph node label and type values are now backed by TEXT columns instead of bounded strings, avoiding failures when generated labels or types exceed 255 characters.
  • Parallel relational setup: Relational database setup is now serialized through an asyncio.Lock, avoiding setup races when multiple add/ingestion calls start at the same time in one process.
  • Cancellation handling for retried LLM and embedding calls: LLM and embedding retry wrappers now treat asyncio.CancelledError as non-retryable, so cancelled tasks stop promptly instead of being held by retry backoff. This affects structured-output LLM adapters and embedding engines across supported providers.
  • KnowledgeGraph subclass extraction: Graph extraction now treats subclasses of KnowledgeGraph as knowledge graph models when integrating chunk graphs and filtering dangling edges. Custom graph models that inherit from KnowledgeGraph now follow the same integration path as the base model instead of being passed through as generic output.

​
v1.1.0.dev1

View on GitHub Developer preview release on the way to v1.1.0dev1. This release includes API, retrieval, permissions, storage-runtime, and backend consistency changes.

​
Highlights

  • Adds database subprocess workers for LanceDB and Kuzu so native database work can run outside the main Cognee process. The wheel now includes the cognee_db_workers package.
  • Exposes more ingestion controls through the public API and remote client paths, including chunk sizing and background execution options for remember() and cognify().
  • Adds dataset_ids support to recall(), making shared-dataset retrieval more reliable when dataset names are not owned by the calling user.
  • Expands permission management with DELETE endpoints for dataset permissions, roles, and user-role membership.
  • Improves session visibility so parent users can see sessions created by child-agent users where appropriate.

​
Notable Changes

  • Adds graph_database_subprocess_enabled and vector_db_subprocess_enabled configuration, plus Kuzu tuning variables for threads, buffer pool size, and max DB size.
  • Keeps belongs_to_set metadata consistent across dataset deletion and shared-node/vector upserts in LanceDB, PGVector, and Neo4j paths.
  • Adds include_payload behavior to Neptune Analytics vector search.
  • Improves Postgres hybrid batching by respecting embedding-engine batch size.
  • Improves infer-schema text sampling and prompting.
  • Rewrites the examples README into a fuller index and adds performance-testing support with Locust.
  • Deprecates .env.example as the canonical template in favor of .env.template.
  • Bumps the package version from 1.0.9 to 1.1.0.dev1 and refreshes lockfiles.

​
v1.0.3

View on GitHub Patch release with bug fixes and stability improvements on top of v1.0.2.

​
Highlights

  • Promotes accumulated dev work to main for the v1.0.3 release
  • Adds session lifecycle APIs, unified memory/session handling, and dashboard support
  • Introduces dataset queueing for async context management and ingestion flows
  • Ships new relational migrations, including session lifecycle tables and parent_user_id
  • Expands recall/remember and cloud routing behavior, plus frontend onboarding and Connect Agent updates

​
Notable Changes

  • Added session endpoints, metrics, and supporting persistence work
  • Added dataset queue infrastructure and follow-up fixes for background processing
  • Added database migrations for new tables and user/dataset ownership handling
  • Updated recall, remember, improve, and search-related API behavior
  • Added frontend work for Connect Agent, dashboard/activity views, API keys, and onboarding
  • Included guide updates, workflow/tooling changes, and dependency updates such as litellm and onnxruntime

​
Bug Fixes

  • PostgreSQL null-byte compatibility: Embedded null bytes (\x00) in node or edge string fields no longer cause errors when using PostgreSQL as the relational backend. Null bytes are now automatically stripped from all string values (including nested attributes) before writes to the relational store. This sanitization is transparent — affected strings are silently cleaned rather than rejected.
  • Fixed duplicate graph nodes caused by DataPoint.id being regenerated during graph construction. The original id is now preserved when converting DataPoint instances into graph nodes, ensuring node identity is stable across graph extraction passes.

​
v1.0.2

View on GitHub Patch release with bug fixes and stability improvements on top of v1.0.1.

​
Bug Fixes

  • LanceDB schema migration: “contained null values” errors (raised when old rows lack a field required by a newer DataPoint schema) are now treated as recoverable schema drift. The affected table is automatically rebuilt from the current schema instead of raising a hard failure.
  • cognee-mcp Docker image build: Added missing build-essential and libpq-dev system packages to the builder stage so that cognee[postgres] can compile psycopg2 from source on Linux.

​
Dependency Updates

  • Bumped llama-index-core requirement from >=0.13.0,<0.14 to >=0.14.20,<0.15 for the llama-index extra.
  • Pinned nltk>=3.9.3,<4 explicitly in the docs extra to satisfy unstructured’s dependency until unstructured v0.21.0.

​
v1.0.1

View on GitHub Patch release with bug fixes on top of v1.0.0.

​
v1.0.0

View on GitHub

​
Highlights

  • New high-level API: remember, recall, improve, and forget cover the full memory lifecycle in four operations
  • Session-aware memory via session_id — short-term context that can be promoted into the permanent graph
  • Unified recall replaces the previous search call with automatic retrieval strategy selection
  • Legacy operations (add, cognify, search, memify) remain available as lower-level building blocks

​
New Features

  • cognee.remember(data, session_id=...) — ingest and graph in one call; supports permanent or session memory
  • cognee.recall(query, session_id=...) — query across both the permanent graph and session cache
  • cognee.improve(...) — enrich an existing graph with feedback-based weighting and session promotion
  • cognee.forget(dataset=..., session_id=...) — delete data, datasets, or full session memory

​
v0.5.4.dev1

Released: March 5, 2026
View on GitHub

​
Highlights

  • Developer preview release focused on quality, performance, and developer ergonomics
  • Faster ingestion and sync
  • Improved search relevance and new filtering options
  • Stability fixes for memory creation, deletion, and CLI workflows
  • Internal refactoring and dependency upgrades

​
New Features

  • Bulk import CLI for faster batched ingestion
  • Search filters for tags and date ranges
  • Optional per-collection ingestion throttling

​
Improvements

  • Lower latency for ingestion and sync
  • Better search ranking
  • More robust deletion and duplicate handling
  • Clearer CLI messages and debug logs

​
Bug Fixes

  • Fixed duplicate memories under concurrent ingestion
  • Fixed partial state after deletion
  • Fixed CLI export formatting issues
  • Fixed intermittent retrieval failures under load

​
v0.5.3

Released: February 27, 2026
View on GitHub

​
Highlights

  • New graph visualization improvements
  • Expanded permissions and user management work
  • SessionManager and cache/session persistence work
  • Search and graph retrieval improvements
  • Multiple stability and CI/CD fixes

​
Notable Changes

  • Added role-based permission checks and permission endpoints
  • Added graph visualization updates, including note set coloring
  • Added return type hints to API functions
  • Added chunk associations for the memify pipeline
  • Added vector filtering based on node sets
  • Fixed delete flow bugs, health check issues, MCP issues, and several config/integration issues

​
v0.5.3.dev1

Released: February 20, 2026
View on GitHub

​
Highlights

  • Added vector filtering based on node sets
  • Added principal Cognee configuration
  • Fixed health check issues
  • Fixed FalkorDB adapter port bug
  • Fixed Ollama image ingestion argument issue

​
Notes

  • Includes a small set of targeted fixes and feature work on top of v0.5.3.dev0
  • Introduced one new contributor in this release