Use and contribute cognee-community packages
Community-maintained plugins live in a separate monorepo:
https://github.com/topoteretes/cognee-community. Everything installable is
under packages/; experimental/ holds demos (n8n nodes, dlt demos,
bauplan, tower) that are not published packages. Each package publishes to
PyPI as cognee-community-<family>-<kind>-<name> and imports as the same
name with underscores.
Package families
| Family |
Packages |
| Vector adapters |
azureaisearch, milvus, moss, opengauss, opensearch, pinecone, qdrant, redis, singlestore, turbopuffer, valkey, weaviate |
| Graph adapters |
arcadedb, memgraph, networkx, pggraph, spanner, turbopuffer, turingdb |
| Hybrid (graph+vector in one DB) |
arcadedb, duckdb, falkordb, helixdb |
| Connectors (data sources) |
confluence, gmail, google-drive, notion, slack |
| Tasks / pipelines / retrievers |
codify_tasks, codify_pipeline, code_retriever, exa_tasks, scrapegraph_tasks |
| Observability |
keywordsai (MONITORING_TOOL=keywordsai + KEYWORDSAI_API_KEY) |
Using a database adapter
Install, then import the package's register module before cognee touches
any engine — registration is what makes the provider name valid:
uv pip install cognee-community-vector-adapter-qdrant
import cognee
from cognee import config
from cognee_community_vector_adapter_qdrant import register # noqa: F401
config.set_vector_db_config({
"vector_db_provider": "qdrant",
"vector_db_url": "http://localhost:6333",
"vector_db_key": "...",
"vector_dataset_database_handler": "qdrant", # only if the adapter ships one
})
The register.py calls use_vector_adapter(name, AdapterClass) /
use_graph_adapter(...). Setting VECTOR_DB_PROVIDER/GRAPH_DATABASE_PROVIDER
to a community name without the register import raises "Unsupported
vector database provider". Hybrid adapters (e.g. falkordb) register as both
graph and vector — set both configs to the same provider name.
Multi-tenancy caveat: with ENABLE_BACKEND_ACCESS_CONTROL=true (the
default), both backends must have a dataset-database handler or cognee raises
EnvironmentError. Community adapters that ship one (registered via
use_dataset_database_handler in their register.py): qdrant, moss,
singlestore, turbopuffer (vector + graph), falkordb, arcadedb, helixdb. All
other community adapters need ENABLE_BACKEND_ACCESS_CONTROL=false.
Using a connector
Connectors expose a dlt source you hand straight to remember(); they
reuse core's DLT ingestion path, so snapshot sync and forget-on-delete work
with no core changes:
from cognee_community_connector_slack import slack_export_source
await cognee.remember(
slack_export_source("/path/to/slack-export"),
dataset_name="team-slack-export", # use a dedicated dataset
max_rows_per_table=0,
)
Same shape for gmail ("ask my inbox"), notion, confluence, and google-drive
(incremental, forget-on-delete). Each package README documents its
credentials; always give a connector its own dataset.
Verifying an install
Every package has examples/example.py (run uv run python examples/example.py
from the package dir) and a tests/ directory. An LLM API key is still
required (LLM_API_KEY, OpenAI by default).
Contributing a package
- Branch from
main — unlike the core repo, cognee-community does not
use a dev branch.
- Follow the existing structure: package dir under
packages/<family>/<name>/
with pyproject.toml, a README.md (install + usage), examples/example.py,
and tests/ that go beyond the example.
- New DB adapters implement
VectorDBInterface / GraphDBInterface from
core, expose a register.py, and should run the shared conformance tests
in packages/shared/contract_suite/ (vector_contract.py / graph_contract.py).
- Add a handler via
use_dataset_database_handler(...) if the backend can
isolate per user+dataset — that's what makes it work with access control on.
- Name it
cognee-community-<family>-<kind>-<name> and add it to the tables
in the repo README. Lint config is the repo-root ruff.toml.
1---
2name: cognee-community
3description: Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify), Keywords AI observability — or wants to contribute a package to the cognee-community repo.
4metadata:
5 source: https://skillmd.com/skills/topoteretes/cognee-community
6---
7
8# Use and contribute cognee-community packages
9
10Community-maintained plugins live in a separate monorepo:
11https://github.com/topoteretes/cognee-community. Everything installable is
12under `packages/`; `experimental/` holds demos (n8n nodes, dlt demos,
13bauplan, tower) that are not published packages. Each package publishes to
14PyPI as `cognee-community-<family>-<kind>-<name>` and imports as the same
15name with underscores.
16
17## Package families
18
19| Family | Packages |
20|---|---|
21| Vector adapters | azureaisearch, milvus, moss, opengauss, opensearch, pinecone, qdrant, redis, singlestore, turbopuffer, valkey, weaviate |
22| Graph adapters | arcadedb, memgraph, networkx, pggraph, spanner, turbopuffer, turingdb |
23| Hybrid (graph+vector in one DB) | arcadedb, duckdb, falkordb, helixdb |
24| Connectors (data sources) | confluence, gmail, google-drive, notion, slack |
25| Tasks / pipelines / retrievers | codify_tasks, codify_pipeline, code_retriever, exa_tasks, scrapegraph_tasks |
26| Observability | keywordsai (`MONITORING_TOOL=keywordsai` + `KEYWORDSAI_API_KEY`) |
27
28## Using a database adapter
29
30Install, then **import the package's `register` module before cognee touches
31any engine** — registration is what makes the provider name valid:
32
33```python
34uv pip install cognee-community-vector-adapter-qdrant
35```
36
37```python
38import cognee
39from cognee import config
40from cognee_community_vector_adapter_qdrant import register # noqa: F401
41
42config.set_vector_db_config({
43 "vector_db_provider": "qdrant",
44 "vector_db_url": "http://localhost:6333",
45 "vector_db_key": "...",
46 "vector_dataset_database_handler": "qdrant", # only if the adapter ships one
47})
48```
49
50The `register.py` calls `use_vector_adapter(name, AdapterClass)` /
51`use_graph_adapter(...)`. Setting `VECTOR_DB_PROVIDER`/`GRAPH_DATABASE_PROVIDER`
52to a community name **without** the register import raises "Unsupported
53vector database provider". Hybrid adapters (e.g. falkordb) register as both
54graph and vector — set both configs to the same provider name.
55
56**Multi-tenancy caveat**: with `ENABLE_BACKEND_ACCESS_CONTROL=true` (the
57default), both backends must have a dataset-database handler or cognee raises
58`EnvironmentError`. Community adapters that ship one (registered via
59`use_dataset_database_handler` in their `register.py`): qdrant, moss,
60singlestore, turbopuffer (vector + graph), falkordb, arcadedb, helixdb. All
61other community adapters need `ENABLE_BACKEND_ACCESS_CONTROL=false`.
62
63## Using a connector
64
65Connectors expose a `dlt` source you hand straight to `remember()`; they
66reuse core's DLT ingestion path, so snapshot sync and forget-on-delete work
67with no core changes:
68
69```python
70from cognee_community_connector_slack import slack_export_source
71
72await cognee.remember(
73 slack_export_source("/path/to/slack-export"),
74 dataset_name="team-slack-export", # use a dedicated dataset
75 max_rows_per_table=0,
76)
77```
78
79Same shape for gmail ("ask my inbox"), notion, confluence, and google-drive
80(incremental, forget-on-delete). Each package README documents its
81credentials; always give a connector its own dataset.
82
83## Verifying an install
84
85Every package has `examples/example.py` (run `uv run python examples/example.py`
86from the package dir) and a `tests/` directory. An LLM API key is still
87required (`LLM_API_KEY`, OpenAI by default).
88
89## Contributing a package
90
91- **Branch from `main`** — unlike the core repo, cognee-community does not
92 use a `dev` branch.
93- Follow the existing structure: package dir under `packages/<family>/<name>/`
94 with `pyproject.toml`, a `README.md` (install + usage), `examples/example.py`,
95 and `tests/` that go beyond the example.
96- New DB adapters implement `VectorDBInterface` / `GraphDBInterface` from
97 core, expose a `register.py`, and should run the shared conformance tests
98 in `packages/shared/contract_suite/` (vector_contract.py / graph_contract.py).
99- Add a handler via `use_dataset_database_handler(...)` if the backend can
100 isolate per user+dataset — that's what makes it work with access control on.
101- Name it `cognee-community-<family>-<kind>-<name>` and add it to the tables
102 in the repo README. Lint config is the repo-root `ruff.toml`.