Cognee CLI

Drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database…

You say
Install this skill Read the source first Free Written by topoteretes · unverified publisher
Context cost
1.6k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 6.6 kBtext throughout, nothing executable
Licence
Apache-2.0free to use
Last change
no release on file
Servers it uses
Noneruns standalone

What it does

Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

memoryknowledge-graphclicognee

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md6.6 kB · 133 lines
--- name: cognee-cli description: Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations. ---
6# Use the cognee CLI
7
8cognee-cli ships with the package (entry point in cognee/cli/_cognee.py;
9each command lives in cognee/cli/commands/). Every command has
10--help with examples — prefer that over guessing flags. Needs
11LLM_API_KEY configured, same as the SDK.
12
13## Core flow
14
15The memory commands are the primary surface as of cognee 1.x:
16
17```bash
18cognee-cli remember "Your text here" # also accepts file paths / URLs
19cognee-cli remember ./docs --dataset-name my_project
20cognee-cli recall "Your question" # query the graph
21cognee-cli recall "keyword" --query-type CHUNKS
22cognee-cli forget --all # wipe local state
23```
24
25remember is ingest + graph build in one step (add + cognify under the
26hood); --background/-b runs the cognify stage in the background, and
27--dry-run estimates LLM tokens/cost without ingesting. recall takes
28--datasets/-d, --top-k/-k (default 10), and --session-id/-s.
29
30forget targets --dataset, --dataset-id, --data-id (needs a dataset), or
31--everything/--all — one unified command covering what delete, prune,
32and empty_dataset used to do separately.
33
34> **forget --all does not ask for confirmation.** It deletes every dataset
35> immediately, even on a non-interactive stdin. The legacy delete --all
36> prompts Delete ALL data from cognee? [y/N] first, so switching to forget
37> silently drops that safety net — script it with care.
38
39Search types match exactly 7 of the SDK's SearchType enum (cognee/modules/search/types/SearchType.py), those 7 being chosen in (cognee/cli/config.py:SEARCH_TYPE_CHOICES):
40GRAPH_COMPLETION, RAG_COMPLETION, CHUNKS, SUMMARIES, CODE, CYPHER, GRAPH_REPORT
41Others must be reached from the SDK, not CLI; e.g. call cognee.recall with query_type=SearchType.TEMPORAL
42
43Note the CLI defaults --query-type to GRAPH_COMPLETION, whereas the SDK's
44cognee.recall() auto-routes when query_type is omitted.
45
46## Session memory and enrichment
47
48Session entries are currently written from the SDK — `cognee.remember(...,
49session_id="chat_1") — not the CLI (cognee-cli remember` has no session
50flag). The CLI side of session memory is reading and bridging:
51
52```bash
53cognee-cli recall "question" -s chat_1 # session cache first: without -d/-t
54 # this searches the session directly
55cognee-cli sessions get # retrieve session Q&A history
56cognee-cli improve -d my_project -s chat_1 # bridge session content into the graph
57cognee-cli improve -d my_project # enrich/index the graph (no session)
58cognee-cli feedback ... # attach feedback to results
59```
60
61improve also takes --node-name, --feedback-alpha (default 0.1), and
62--background/-b. remember/improve build their graphs through
63cognify(), so cognify-level settings (e.g. CONTRADICTION_DETECTION=true)
64apply to them too.
65
66## Legacy / lower-level commands
67
68add, cognify, search, memify, and delete still ship and are what the
69memory commands call underneath. Use them only to drive a single stage in
70isolation; prefer remember/recall/forget/improve otherwise.
71
72```bash
73cognee-cli add "text" && cognee-cli cognify # what remember does in one step
74cognee-cli search "question" # recall minus routing/scope/session sources
75cognee-cli memify -d my_project # custom extraction/enrichment tasks
76cognee-cli delete --all # superseded by forget --all
77```
78
79## Management
80
81```bash
82cognee-cli datasets list # dataset operations
83cognee-cli config get [key] [--show-secrets] # view one/all settings (API keys masked by default)
84cognee-cli config set <key> <value> # set + persist to ./.env in the cwd
85cognee-cli config unset <key> # reset a key to its default (also persisted)
86cognee-cli -ui # launch API server + UI (see cognee-server skill)
87cognee-cli serve --url http://localhost:8000 # connect CLI/SDK to a running instance
88```
89
90## Relational DB migrations (Alembic)
91
92```bash
93cognee-cli upgrade # apply migrations
94cognee-cli downgrade
95cognee-cli history
96cognee-cli current
97```
98
99Typically needed after version upgrades when the server refuses to start on
100an old schema.
101
102## Gotchas
103
104- The CLI initializes cognee lazily; the first command in a fresh environment
105 is slow (DB + model setup), later ones are fast.
106- remember (and add) without --dataset-name targets the default dataset
107 main_dataset; recall/search operate across your accessible datasets
108 unless a dataset is given.
109- forget refuses to run bare — pass --dataset, --dataset-id, --data-id
110 (with a dataset), or --everything/--all.
111- Session commands (recall -s, sessions get, improve -s) require
112 CACHING=true (the default) — with it off, session reads return nothing and
113 SDK session writes raise. To cut read latency and token cost while keeping
114 session memory, cognee-cli config set AUTO_FEEDBACK false — by default
115 cognee makes one structured-output LLM call per answered query to self-tune
116 its memory.
117- memify requires one of the arguments -d/--dataset-name --dataset-id
118- config set/config unset write to the .env file in whatever directory
119 you run the command from (creating it if missing). config reset (reset
120 *all* keys) is still not implemented.
121- **Which .env actually wins is not always the cwd one.** At import, cognee
122 calls dotenv.load_dotenv(override=True), which resolves relative to the
123 *cognee package location*, not your working directory. In a source/editable
124 checkout (uv pip install -e .) a .env at the repo root therefore shadows
125 the .env in the directory you ran from — and because override=True, it
126 also beats variables you exported. Symptom: config set appears to do
127 nothing, or the CLI connects to a backend you thought you had overridden.
128 To test against different settings, move the repo .env aside, or set
129 values programmatically after import (cognee.config.set_*). (Under
130 python -c the cwd .env does win, because dotenv falls back to the cwd
131 when __main__ has no __file__ — which is why the same command can
132 behave differently as a script vs. -c.)
133
In the file
SKILL.md874 words
Files1
LicenceApache-2.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈50
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,600
on trigger
The instruction body, read only when the skill fires.
0.83%
of a 200k window
Ten skills this size would take about 8% of the window before you open a file.
050k100k150k200k context window

1.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 6.6 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md6.6 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Cognee CLI · 1.6k tokens when loaded npx mcprush@latest skill add topoteretes/cognee-cli

Writes to .claude/skills/cognee-cli/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencetopoteretes/cognee-cli

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v
  • No earlier releases have been published to the marketplace.
Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

TO
topoteretes

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill