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.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
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) |
Use the cognee_recall tool to search for existing related content before storing, then use a bash command to POST to the running Cognee server's remember endpoint:
User data (preferences, corrections, personal context):
curl -s -X POST "${COGNEE_BASE_URL:-http://localhost:8011}/api/v1/remember" \
-H "X-Api-Key: ${COGNEE_API_KEY:-}" \
-F "datasetName=${COGNEE_PLUGIN_DATASET:-agent_sessions}" \
-F "node_set=user_context" \
-F "run_in_background=false" \
-F "data=$ARGUMENTS"
Project data (docs, code, company knowledge):
curl -s -X POST "${COGNEE_BASE_URL:-http://localhost:8011}/api/v1/remember" \
-H "X-Api-Key: ${COGNEE_API_KEY:-}" \
-F "datasetName=${COGNEE_PLUGIN_DATASET:-agent_sessions}" \
-F "node_set=project_docs" \
-F "run_in_background=false" \
-F "data=$ARGUMENTS"
Agent data (explicit agent notes — routine tool logs are automatic):
curl -s -X POST "${COGNEE_BASE_URL:-http://localhost:8011}/api/v1/remember" \
-H "X-Api-Key: ${COGNEE_API_KEY:-}" \
-F "datasetName=${COGNEE_PLUGIN_DATASET:-agent_sessions}" \
-F "node_set=agent_actions" \
-F "run_in_background=false" \
-F "data=$ARGUMENTS"
A {"ok": true} response means the server accepted the data. An error response means the server rejected or failed the request — check COGNEE_API_KEY and server logs; do not re-run or conclude the data wasn't stored without confirming against the server.
IMPORTANT: The remember call always runs in the foreground (run_in_background=false) to ensure the full pipeline completes before returning.
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) |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when indexing a code repository into Cognee's code graph or querying it (callers, impact analysis, paths, endpoints) from Codex.
The English summary is being prepared. Showing the original description.
Use when indexing a code repository into Cognee's code graph or querying it (callers, impact analysis, paths, endpoints) from Antigravity.
The English summary is being prepared. Showing the original description.
Explain a repository's architecture (modules, routes, storage, services), find risky hotspots, draw a Mermaid diagram of the code graph, or review how far a change reaches, from Cognee's code graph.
The English summary is being prepared. Showing the original description.
Index a repository (local path or git URL) into Cognee's code graph and answer exact structural queries with no LLM calls: callers, dependencies, impact of changing a symbol, call paths, endpoints, re-index changes.
The English summary is being prepared. Showing the original description.
A digest of a week or more of the user's own coding-agent sessions (default 7 days): sessions per day and project, most-edited files and the lessons Cognee learned, written up as shipped, decided and still open.
The English summary is being prepared. Showing the original description.
A multi-day digest of the user's own coding-agent sessions — sessions per day and project, most-edited files, and every lesson Cognee distilled into the knowledge graph in that window. Use only when the user explicitly asks for a weekly digest, a retro, a recap or report of their recent sessions, or asks for the `cognee-digest` skill by name. Not for questions about code or the current task.
The English summary is being prepared. Showing the original description.