Skip to main content
Add persistent memory to Claude Code backed by your Cognee Cloud tenant with the Cognee memory plugin — no code and no pip install. The plugin hooks into Claude Code’s lifecycle: it captures your prompts, tool traces, and answers into session memory, injects relevant context on every prompt, and syncs the session into your knowledge graph on session end. Sessions are disposable; your memory isn’t.

​
1. Install the plugin

Install from the Claude Code marketplace before launching Claude Code, so the first claude launch is a clean session that runs the plugin bootstrap automatically:
These CLI subcommands use the same plugin manager as the in-chat /plugin commands. If you instead install from inside the chat with /plugin, restart Claude Code (start a new session) before memory connects — /reload-plugins loads the skills but does not run SessionStart.
Install scope defaults to user (global). Pass --scope project or --scope local to confine the plugin to a single repo.
On the first clean launch you’ll see a “Cognee Memory Connected” message, and the status line shows cognee: <dataset> · <mode>.

​
2. Point it at Cognee Cloud

Set both variables in the shell that launches Claude Code, using your tenant base URL and an API key:
When COGNEE_BASE_URL is set, the plugin runs as a pure thin HTTP client to your tenant — it does not install a local Cognee runtime. When COGNEE_BASE_URL is unset, the plugin instead bootstraps a local API at http://localhost:8011. Setting the Cloud URL and key is what routes memory to your tenant.

​
3. Choose a dataset

All writes and recall are scoped to a single dataset, selected with the COGNEE_PLUGIN_DATASET environment variable. By default both the Claude Code and Codex plugins use agent_sessions, so memory is shared across both integrations automatically. Set a custom dataset at launch:
The dataset is fixed for the lifetime of a launch, and recall searches only the active dataset. To switch datasets, exit Claude Code, change COGNEE_PLUGIN_DATASET, and start it again. The dataset key in ~/.cognee-plugin/claude-code/config.json is informational-only — runtime dataset selection reads the env var, not the config file.
Data added to the same dataset outside Claude Code (via the SDK or the server) is visible in Claude Code through the plugin.

​
4. Pick a session (optional)

By default a new session_id is generated on each launch. Set COGNEE_SESSION_ID to resume a specific named session, or to deliberately share one live session across two terminals:

​
5. Verify

Restart Claude Code so SessionStart runs with the new credentials, then open a fresh session and ask:
What do you know from cognee?
Answering from a clean session confirms it’s recalling from your Cloud memory. You can also invoke the skills explicitly:
Memory is captured and synced from your sessions over time, and writes build the graph in the background — so a brand-new setup may recall nothing until at least one session has synced. An empty first recall is expected.
Share specific datasets with connected agents from the Connections page to grant scoped read access.

​
Configuration reference

Precedence: environment variables → ~/.cognee-plugin/claude-code/config.json → defaults. See the full integration guide for the idle-watcher, session-sync, and update-notification variables.

Full integration guide

Hooks reference, session sync, and debugging

Codex

The same memory plugin for the Codex CLI