원클릭으로
cognee-remember
// Store data permanently in the Cognee knowledge graph. Accepts a data category (user, project, or agent) to tag the data with the correct node_set for filtered retrieval.
// Store data permanently in the Cognee knowledge graph. Accepts a data category (user, project, or agent) to tag the data with the correct node_set for filtered retrieval.
Use when ingesting, cognifying, or querying a codebase with Cognee CLI from Codex.
Use when launching, checking, or reporting on the local Cognee UI/backend through cognee-cli -ui.
Use when Codex should remember, recall, search, improve, or forget information using the Cognee CLI.
Use when setting up, checking, or connecting Cognee through the cognee CLI from Codex.
Search Cognee memory. Session memory is automatically searched on every prompt via hooks. Use this skill explicitly for permanent knowledge graph search, filtered category search, or when you need more results than the automatic lookup provides.
Sync session cache entries into the permanent Cognee knowledge graph. Run this to make session memory searchable, or it runs automatically at session end.
| name | cognee-remember |
| description | Store data permanently in the Cognee knowledge graph. Accepts a data category (user, project, or agent) to tag the data with the correct node_set for filtered retrieval. |
Store data permanently in the Cognee knowledge graph with category tagging.
Cognee organizes knowledge into three categories via node_set tagging:
| Category | Node set | What belongs here |
|---|---|---|
| user | user_context | User preferences, corrections, personal facts, communication style |
| project | project_docs | Repository docs, code context, architecture decisions, company data |
| agent | agent_actions | Tool call logs, reasoning traces, generated artifacts (auto-captured by hooks) |
Determine the category from the user's intent, then run:
User data (preferences, corrections, personal context):
cognee-cli remember "$ARGUMENTS" -d "${COGNEE_PLUGIN_DATASET:-claude_sessions}" --node-set user_context
Project data (docs, code, company knowledge):
cognee-cli remember "$ARGUMENTS" -d "${COGNEE_PLUGIN_DATASET:-claude_sessions}" --node-set project_docs
Agent data (explicit agent notes — routine tool logs are automatic):
cognee-cli remember "$ARGUMENTS" -d "${COGNEE_PLUGIN_DATASET:-claude_sessions}" --node-set agent_actions
If the category is unclear, default to project.
The command outputs a summary after completion:
Data ingested and knowledge graph built successfully!
Dataset ID: aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee
Items processed: 1
Content hash: a1b2c3d4...
Elapsed: 4.2s
IMPORTANT: Do NOT use the -b (background) flag. Always run in the foreground to ensure the full pipeline completes.
agent_actions tagging)| Signal | Category |
|---|---|
| "remember my preference for..." | user |
| "I always want..." / "I prefer..." | user |
| "remember this about the codebase" | project |
| "save these docs" / "index this file" | project |
| "note that this API works like..." | project |
| "remember what we discovered" | agent |
| Routine tool calls | agent (automatic, no action needed) |