RAG Implementation
wshobson/agents
Build retrieval-augmented generation systems: pick a vector database and embedding model, choose retrieval and reranking strategies, and start from a LangGraph pipeline.
Guide to using and contributing cognee community packages: database adapters, data-source connectors, custom tasks and retrievers, and Keywords AI observability.
Install Cognee Community Packages
$ npx skills add topoteretes/cognee --skill cognee-community -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install topoteretes/cognee cognee-community --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cognee-community .claude/skills/cognee-community && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cognee-community" agent skill from https://github.com/topoteretes/cognee/tree/main/.agents/skills/cognee-community into .claude/skills/cognee-community/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognee-community", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/topoteretes/cognee/tree/main/.agents/skills/cognee-communityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add topoteretes/cognee --skill cognee-community -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install topoteretes/cognee cognee-community --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/cognee-community .agents/skills/cognee-community && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cognee-community" agent skill from https://github.com/topoteretes/cognee/tree/main/.agents/skills/cognee-community into .agents/skills/cognee-community/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognee-community", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add topoteretes/cognee --skill cognee-community -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install topoteretes/cognee cognee-community --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/cognee-community .cursor/skills/cognee-community && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cognee-community" agent skill from https://github.com/topoteretes/cognee/tree/main/.agents/skills/cognee-community into .cursor/skills/cognee-community/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognee-community", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/topoteretes/cognee.git --path .agents/skills/cognee-community--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add topoteretes/cognee --skill cognee-community -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install topoteretes/cognee cognee-community --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/cognee-community .gemini/skills/cognee-community && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cognee-community" agent skill from https://github.com/topoteretes/cognee/tree/main/.agents/skills/cognee-community into .gemini/skills/cognee-community/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognee-community", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install topoteretes/cognee cognee-communityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add topoteretes/cognee --skill cognee-community -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/cognee-community .github/skills/cognee-community && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cognee-community" agent skill from https://github.com/topoteretes/cognee/tree/main/.agents/skills/cognee-community into .github/skills/cognee-community/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognee-community", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add topoteretes/cognee --skill cognee-community -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install topoteretes/cognee cognee-community --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/topoteretes/cognee.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/cognee-community .opencode/skills/cognee-community && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cognee-community" agent skill from https://github.com/topoteretes/cognee/tree/main/.agents/skills/cognee-community into .opencode/skills/cognee-community/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cognee-community", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cognee-community- GitHub stars
- 32k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 396 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Guide to using and contributing cognee community packages: database adapters, data-source connectors, custom tasks and retrievers, and Keywords AI observability.
- Using a community vector or graph database adapter with cognee
- SKILL.md covers Package families, Using a database adapter, Using a connector and Verifying an install, plus 1 more section
- Calls uv; needs KEYWORDSAI_API_KEY and LLM_API_KEY
- Connecting Slack, Gmail, Notion, Confluence or Google Drive as a cognee data source
What it does
Community plugins for cognee, the AI memory platform, live in a separate monorepo, and this skill explains how to use and contribute them. Installable packages sit under `packages/`, grouped into vector adapters (Qdrant, Milvus, Pinecone, Redis, Weaviate and others), graph adapters, hybrid graph-plus-vector adapters (such as DuckDB and FalkorDB), data-source connectors (Confluence, Gmail, Google Drive, Notion, Slack), custom tasks and retrievers, and a Keywords AI observability package. Demos under `experimental/` are not published packages.
To use an adapter, install its package and import its `register` module before cognee touches any engine, because registration is what makes the provider name valid; without it cognee raises an unsupported-provider error. Hybrid adapters register as both graph and vector, so both settings take the same name. With backend access control on, the default, both backends need a dataset-database handler, and only some adapters ship one (qdrant, moss, singlestore, turbopuffer, falkordb, arcadedb, helixdb); the rest require turning access control off. Connectors expose a dlt source that is handed to `remember()`.
When your agent uses it
- Using a community vector or graph database adapter with cognee
- Connecting Slack, Gmail, Notion, Confluence or Google Drive as a cognee data source
- Fixing an unsupported provider error after selecting a community adapter
- Contributing a new package to the cognee-community repository
Example prompts
- “Configure cognee to use the Qdrant community adapter for vectors.”
- “I set VECTOR_DB_PROVIDER to milvus and get an unsupported provider error. What is missing?”
- “Ingest my Notion workspace into cognee with the community connector.”
- “How do I package a new graph adapter for cognee-community?”
Requirements
- The cognee Python package
- The cognee-community package for the chosen adapter or connector, installed with uv or pip
What it can do on your machine
Read from SKILL.md and the folder at commit 0ec7a9f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
KEYWORDSAI_API_KEYLLM_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cognee Community Packages loads about 1.2k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 396 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from topoteretes/cognee at commit 0ec7a9f, republished under its Apache-2.0 licence (© topoteretes). 396 words, ~1,163 tokens.
Download SKILL.mdSave it as
.claude/skills/cognee-community/SKILL.md (or your agent's skills folder).- name
- cognee-community
- description
- 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.
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-qdrantimport 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.
Show full SKILL.md (132 more words)Show less
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 adevbranch. - Follow the existing structure: package dir under
packages/<family>/<name>/withpyproject.toml, aREADME.md(install + usage),examples/example.py, andtests/that go beyond the example. - New DB adapters implement
VectorDBInterface/GraphDBInterfacefrom core, expose aregister.py, and should run the shared conformance tests inpackages/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-rootruff.toml.
© topoteretes, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/cognee-community of topoteretes/cognee.
Open the folder on GitHubat commit 0ec7a9f
Compare with similar skills
Cognee Community Packages next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cognee Community Packages this skilltopoteretes/cognee | 32k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| RAG Implementationwshobson/agents | 40k | 9 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Hunt RAG Vectorelementalsouls/Claude-BugHunter | 4.8k | — | ~2.6k | Automated safety check: Pass | MIT | |
| Vector Database Engineeraiskillstore/marketplace | 433 | 7 repos | ~563 | Automated safety check: Pass | None | |
| Qdrant Migration Toolqdrant/skills | 254 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Neo4j Graphrag Skillneo4j-contrib/neo4j-skills | 114 | — | ~4.2k | Automated safety check: Notes | MIT |
Similar skills
Hunt RAG Vector
elementalsouls/Claude-BugHunter
Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from…
Vector Database Engineer
aiskillstore/marketplace
Expert in vector databases, embedding strategies, and semantic search implementation.
- Official
Qdrant Migration Tool
qdrant/skills
Guides use of the Qdrant Migration Tool CLI to move vectors, metadata, and sparse embeddings from another vector database into Qdrant.
Neo4j Graphrag Skill
neo4j-contrib/neo4j-skills
Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+).
Using Vector Databases
ancoleman/ai-design-components
Vector database implementation for AI/ML applications, semantic search, and RAG systems.
More from topoteretes/cognee
All 19 skills in this repoCognee CLI Memory Commands
topoteretes/cognee
Drives cognee from the terminal with remember, recall, forget and improve memory commands, dataset and config management and database migrations.
Cognee Custom Graph Models
topoteretes/cognee
Defines the shape of cognee's knowledge graph with graph_model: DataPoint node classes, identity and index fields, typed edges and fixes for duplicated nodes.
Cognee Custom Pipelines
topoteretes/cognee
Shows how to write custom cognee tasks, chain them into pipelines, store custom DataPoints and run enrichment over the existing graph.
Cognee Docker Setup
topoteretes/cognee
Runs the Cognee AI memory platform in Docker, from a one-file prebuilt image to a full compose stack with UI, MCP server, Postgres and Neo4j.
Cognee Forget
topoteretes/cognee
Removes data from cognee memory with forget(), finding the right dataset and document first and choosing between one document, a dataset or only the graph and vector memory.
Cognee Session Memory and Improve
topoteretes/cognee
Explains how cognee stores session memory by session_id and bridges it into the permanent graph with improve(), including the stages, results and settings.
Related
Categories
Questions about Cognee Community Packages
What does Cognee Community Packages do?
Guide to using and contributing cognee community packages: database adapters, data-source connectors, custom tasks and retrievers, and Keywords AI observability. Community plugins for cognee, the AI memory platform, live in a separate monorepo, and this skill explains how to use and contribute them. Installable packages sit under `packages/`, grouped into vector adapters (Qdrant, Milvus, Pinecone, Redis, Weaviate and others), graph adapters, hybrid graph-plus-vector adapters (such as DuckDB and FalkorDB), data-source connectors (Confluence, Gmail, Google Drive, Notion, Slack), custom tasks and retrievers, and a Keywords AI observability package.
When should I use Cognee Community Packages?
Cognee Community Packages fits situations like: using a community vector or graph database adapter with cognee; connecting Slack, Gmail, Notion, Confluence or Google Drive as a cognee data source; fixing an unsupported provider error after selecting a community adapter; contributing a new package to the cognee-community repository.
How do I install Cognee Community Packages in Claude Code?
Run `npx skills add topoteretes/cognee --skill cognee-community -a claude-code`. Or copy the skill folder (.agents/skills/cognee-community in topoteretes/cognee) into .claude/skills/cognee-community in your project. Claude Code loads it when a task matches its description.
How do I install Cognee Community Packages in Codex?
Run `npx skills add topoteretes/cognee --skill cognee-community -a codex`. Or copy the skill folder (.agents/skills/cognee-community in topoteretes/cognee) into .agents/skills/cognee-community in your project. Codex loads it when a task matches its description.
Can I use Cognee Community Packages in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add topoteretes/cognee --skill cognee-community -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cognee-community, .gemini/skills/cognee-community, .github/skills/cognee-community and .opencode/skills/cognee-community in your project.
What does Cognee Community Packages need to run?
Going by SKILL.md and its folder, Cognee Community Packages needs the command-line tools its instructions call (uv) and credentials named KEYWORDSAI_API_KEY and LLM_API_KEY. Our summary lists: The cognee Python package; The cognee-community package for the chosen adapter or connector, installed with uv or pip.
Does Cognee Community Packages access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Cognee Community Packages safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Cognee Community Packages use?
Cognee Community Packages is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cognee Community Packages use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Cognee Community Packages?
Skills that share tags, products or a category with Cognee Community Packages: RAG Implementation (wshobson/agents, 40k stars), Hunt RAG Vector (elementalsouls/Claude-BugHunter, 4.8k stars), Vector Database Engineer (aiskillstore/marketplace, 433 stars) and Qdrant Migration Tool (qdrant/skills, 254 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cognee Community Packages?
topoteretes (a GitHub organization) maintains it in topoteretes/cognee, which has 31,919 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 9, 2026.
Source: topoteretes/cognee on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.