cognee-cli skill

Use the cognee CLI

cognee-cli ships with the package (entry point in cognee/cli/cognee.py; each command lives in cognee/cli/commands/). Every command has --help for its flags, but only a few (memify, eval, serve, push, migrate) include usage examples — for the memory commands use the examples in this file. Needs LLMAPI_KEY configured, same as the SDK.

Core flow

The memory commands are the primary surface as of cognee 1.x:

cognee-cli remember "Your text here"         # also accepts file paths / URLs
cognee-cli remember ./docs --dataset-name my_project
cognee-cli recall "Your question"            # query the graph
cognee-cli recall "keyword" --query-type CHUNKS
cognee-cli forget --all                      # wipe local state

remember is ingest + graph build in one step (add + cognify under the hood); --background/-b runs the cognify stage in the background, and --dry-run estimates LLM tokens/cost without ingesting. recall takes --datasets/-d, --top-k/-k (default 10), and --session-id/-s.

forget targets --dataset, --dataset-id, --data-id (needs a dataset), or --everything/--all — one unified command covering what delete, prune, and empty_dataset used to do separately.

forget --all does not ask for confirmation. It deletes every dataset

immediately, even on a non-interactive stdin. The legacy delete --all

prompts Delete ALL data from cognee? [y/N] first, so switching to forget

silently drops that safety net — script it with care.

--query-type accepts 10 of the SDK's 20 SearchType values — the list in cognee/cli/config.py:SEARCHTYPECHOICES: HYBRIDCOMPLETION, GRAPHCOMPLETION, RAGCOMPLETION, CHUNKS, CHUNKSLEXICAL, SUMMARIES, CODE, CYPHER, GRAPHREPORT, SKILLS. The rest (TEMPORAL, TRIPLETCOMPLETION, GRAPHCOMPLETIONCOT, AGENTICCOMPLETION, NATURALLANGUAGE, …) are SDK-only, e.g. cognee.recall(q, query_type=SearchType.TEMPORAL).

When --query-type is omitted the CLI uses HYBRIDCOMPLETION (DEFAULTSEARCH_TYPE), whereas the SDK's cognee.recall() auto-routes between search types. --top-k defaults to 10 on the CLI and 15 in the SDK.

Session memory and enrichment

Session entries are currently written from the SDK — cognee.remember(..., sessionid="chat1") — not the CLI (cognee-cli remember has no session flag). The CLI side of session memory is reading and bridging:

cognee-cli recall "question" -s chat_1       # session cache first: without -d/-t
                                             # this searches the session directly
cognee-cli sessions get                      # retrieve session Q&A history
cognee-cli improve -d my_project -s chat_1   # bridge session content into the graph
cognee-cli improve -d my_project             # enrich/index the graph (no session)
cognee-cli feedback ...                      # attach feedback to results

improve also takes --node-name, --feedback-alpha (learning rate in (0, 1]; default IMPROVEFEEDBACKALPHA, 0.1), --build-global-context-index, --build-truth-subspace (both opt-in stages; the truth subspace needs -s), and --background/-b. It prints one line per stage — name, status (completed / alreadycompleted / skipped / errored) and the skip reason (e.g. nosessionids, lockheld, tripletembeddingdisabled). remember/improve build their graphs through cognify(), so cognify-level settings (e.g. CONTRADICTION_DETECTION=true) apply to them too.

Legacy / lower-level commands

add, cognify, search, memify, and delete still ship and are what the memory commands call underneath. Use them only to drive a single stage in isolation; prefer remember/recall/forget/improve otherwise.

cognee-cli add "text" && cognee-cli cognify  # what `remember` does in one step
cognee-cli search "question"                 # `recall` minus routing/scope/session sources
cognee-cli memify -d my_project              # custom extraction/enrichment tasks
cognee-cli delete --all                      # superseded by `forget --all`

Management

cognee-cli datasets list                     # dataset operations
cognee-cli config get [key] [--show-secrets] # view one/all settings (API keys masked by default)
cognee-cli config set <key> <value>          # set + persist to ./.env in the cwd
cognee-cli config unset <key>                # reset a key to its default (also persisted)
cognee-cli -ui                               # launch API server + UI (see cognee-server skill)
cognee-cli serve --url http://localhost:8000 # connect CLI/SDK to a running instance

Relational DB migrations (Alembic)

cognee-cli upgrade        # apply migrations
cognee-cli downgrade
cognee-cli history
cognee-cli current

Typically needed after version upgrades when the server refuses to start on an old schema.

Gotchas

is slow (DB + model setup), later ones are fast.

• The CLI initializes cognee lazily; the first command in a fresh environment

main_dataset; recall/search operate across your accessible datasets unless a dataset is given.

• remember (and add) without --dataset-name targets the default dataset

(with a dataset), or --everything/--all.

• forget refuses to run bare — pass --dataset, --dataset-id, --data-id

CACHING=true (the default) — with it off, session reads return nothing and SDK session writes raise. To cut read latency and token cost while keeping session memory, cognee-cli config set AUTO_FEEDBACK false — by default cognee makes one structured-output LLM call per answered query to self-tune its memory.

• Session commands (recall -s, sessions get, improve -s) require

you run the command from (creating it if missing). config reset (reset all keys) is still not implemented.

• memify requires one of the arguments -d/--dataset-name --dataset-id
• config set/config unset write to the .env file in whatever directory

calls dotenv.loaddotenv(override=True), which resolves relative to the cognee package location, not your working directory. In a source/editable checkout (uv pip install -e .) a .env at the repo root therefore shadows the .env in the directory you ran from — and because override=True, it also beats variables you exported. Symptom: config set appears to do nothing, or the CLI connects to a backend you thought you had overridden. To test against different settings, move the repo .env aside, or set values programmatically after import (cognee.config.set). (Under python -c the cwd .env does win, because dotenv falls back to the cwd when main has no file — which is why the same command can behave differently as a script vs. -c.)

• Which .env actually wins is not always the cwd one. At import, cognee