- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add topoteretes/cognee --skill cognee-forget -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add topoteretes/cognee --skill cognee-forget -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add topoteretes/cognee --skill cognee-forget -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add topoteretes/cognee --skill cognee-forget -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/topoteretes/cognee/tree/HEAD/.agents/skills/cognee-forgetDo publicador
forget() is cognee's one deletion API. It removes one document, a whole
dataset, or only the derived memory (graph + vectors) while keeping the raw
files. Deletion cannot be undone, so the workflow is always find, read,
confirm, then delete.
Hard limits for agents
- Delete only what the user asked to forget. Identify it by reading the content first; never guess from a file name alone.
- Confirm the exact items with the user before deleting, unless they already named exact ids.
- The widest deletion you may run is
forget(everything=True), and only when the user explicitly asks to wipe all of their memory. Never use any other reset or wipe mechanism to delete data.
import cognee
datasets = await cognee.datasets.list_datasets() # datasets the user can read
for ds in datasets:
print(ds.id, ds.name)
HTTP: GET /api/v1/datasets. CLI: cognee-cli datasets list.
items = await cognee.datasets.list_data(dataset_id) # all Data rows, oldest first
for item in items:
print(item.id, item.name, item.extension, item.created_at)
HTTP: GET /api/v1/datasets/{dataset_id}/data?limit=100&offset=0 (limit up
to 1000; GET .../data/count for the total; example:
examples/python/dataset_data_pagination.py). CLI:
cognee-cli datasets data <dataset_uuid>.
Each item has id, name, created_at, extension, mime_type,
raw_data_location, dataset_id, label, external_metadata (including
any node_set), and data_size.
Names are often text_<hash>.txt, so read the content to find what the user
means.
GET /api/v1/datasets/{dataset_id}/data/{data_id}/raw returns the
stored file (404 if it is gone).from cognee.infrastructure.files.utils.open_data_file import open_data_file
async with open_data_file(item.raw_data_location, mode="rb") as f:
preview = f.read(2000).decode("utf-8", errors="replace")
Judge matches by meaning, not only by keywords, and show the user the candidates (name + a short preview) before deleting.
Return values: {"data_id", "dataset_id", "search_history_removed", "status"}
for a document, {"dataset_id", "search_history_removed", "status"} for a
dataset (plus data_records_reset with memory_only), {"datasets_removed", "search_history_removed", "status"} for everything (datasets_removed
counts the datasets the user can read, not the delete set).
search_history_removed is True for a dataset or everything forget: every
recorded question and answer for the deleted datasets is gone, whoever asked.
It does not cover rows saved without a dataset (history from before cognee
1.5.0, or a search over several datasets with access control off): a dataset
forget leaves them, and an everything forget removes only the caller's own.
It is False for a document forget, which never purges history (rows are
recorded per dataset, so answers that quoted the document stay until the
dataset itself is forgotten). clean_history=True on any forget deletes the
caller's own history first (every row this user owns, in any dataset) and
the result carries history_cleaned: True; without it a document forget
reports history_cleaned: False. If a history purge fails, the forget raises
before any data is deleted, so retry the same forget.
HTTP: POST /api/v1/forget with a JSON body; camelCase and snake_case
keys both work: {"datasetId": "...", "dataId": "..."},
{"dataset": "name", "memoryOnly": true}, {"everything": true}. Invalid
combinations return 422.
CLI: cognee-cli forget --dataset NAME | --dataset-id UUID [--data-id UUID] [--memory-only], or --everything / --all. The CLI
does not ask for confirmation; confirm with the user first.
data_id that is not in the dataset returns success and deletes
nothing. The delete path treats an unknown id as a custom-graph-model
delete. Always take the id from list_data for that same dataset, and
check it is still listed afterwards if it matters.dataset or dataset_id, not both (ValueError).
data_id and memory_only both need a dataset.memory_only is ignored when everything=True in the SDK (the CLI
rejects the combination). everything=True always deletes everything.memory_only is not deletion. The raw file and
the data row are still there and the next cognify re-processes them. Use a
plain forget(dataset=...) or forget(data_id=...) to remove the data.DatasetNotFoundError. Deleting
needs the delete permission on the dataset (see the cognee-permissions
skill). everything=True deletes every dataset the user has delete
permission on in the current tenant, including datasets shared to them
with delete rights, not only the ones they own.cognee.update(data_id=..., data=..., dataset_id=...), which keeps its
id and re-extracts only the changed parts.cognee.delete() is deprecated; use forget().forget() resolves the dataset with the delete permission, then:
datasets.delete_data(): takes the dataset lock,
deletes the graph nodes and edges the document owns, the matching vectors
and edge evidence, invalidates sessions that cited them, then deletes the
Data row. Ownership is tracked per document (source-refs on graph
elements), so an entity shared by two documents survives until both are
deleted. Raw files are reference-counted by storage location.datasets.empty_dataset().memory_only → drops the dataset's graph/vector memory and resets its
pipeline status, leaving raw data for a rebuild.everything → datasets.delete_all() over every dataset the user has
delete on in the current tenant, plus a full prune of the session cache
(when caching or usage logging is on). This wipes every user's
sessions (Redis FLUSHDB / all SQL cache tables), not
just this user's.Key files:
cognee/api/v1/forget/forget.py (SDK), routers/get_forget_router.py
(HTTP), cognee/cli/commands/forget_command.py (CLI)cognee/api/v1/datasets/datasets.py (list_datasets, list_data,
delete_data, empty_dataset, delete_all)cognee/api/v1/datasets/routers/get_datasets_router.py (list, count, raw)cognee/infrastructure/databases/provenance/source_refs.py (per-document
ownership of graph elements)cognee/infrastructure/files/utils/open_data_file.pyforget(data_id=...) cannot find and remove it.memory_only.forget() are in cognee/tests/unit/api/v1/forget/
(argument validation, the HTTP endpoint, memory_only); cover both the
document and the memory_only paths for new deletion behaviour.Use when removing data from cognee memory with forget() in the SDK, HTTP API, or CLI — finding which dataset and document hold the content to delete (listing datasets and data items, reading raw conte
---name: cognee-forgetdescription: Use when removing data from cognee memory with forget() in the SDK, HTTP API, or CLI — finding which dataset…---# .agents/skills/cognee-forget/SKILL.mdVisão geral
Use when removing data from cognee memory with forget() in the SDK, HTTP API, or CLI — finding which dataset and document hold the content to delete (listing datasets and data items, reading raw content), choosing between deleting one document, a whole dataset, or only the graph/vector memory, and doing it safely.
Perguntas frequentes
Baixe .agents/skills/cognee-forget/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/topoteretes/cognee.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.