Dejavu

Deja Vu Plugin for Claude Code, Claude Cowork, Cursor & Codex

Add persistent memory to your AI workflows. Store, retrieve, and manage memories across sessions using the Deja Vu Platform. Works with Claude Code (CLI), Claude Cowork (desktop app), Cursor, and Codex.

Quick path for agents

If you're an AI agent setting up Deja Vu autonomously (no human dashboard signup available), run:

dejavu init --agent --json

This mints an evaluation API key in <5 seconds — no email, no OTP, no browser. The key is written to your config and exported as VENICE_API_KEY for the current shell. Use it immediately against the Deja Vu Platform or the MCP server. The human owner can later run dejavu init --email <their-email> to claim ownership: memories transfer, the same API key keeps working, and the agent isn't disrupted.

Humans setting up Deja Vu by hand should continue with Step 1 below.

Step 1: Set your API key

You must complete this step before installing the plugin.

1. Sign up at app.dejavu.ai if you haven't already

2. Go to app.dejavu.ai/dashboard/api-keys

3. Click Create API Key and copy the key (starts with m0-)

4. Add it to your shell profile:

   # For zsh (default on macOS)
   echo 'export VENICE_API_KEY="m0-your-api-key"' >> ~/.zshrc
   source ~/.zshrc
   
   # For bash
   echo 'export VENICE_API_KEY="m0-your-api-key"' >> ~/.bashrc
   source ~/.bashrc
   

5. Confirm it's set:

   echo $VENICE_API_KEY
   # Should print: m0-your-api-key
   

Step 2: Install the plugin

Choose one of the options below. All require VENICE_API_KEY to be set first (see above).

Claude Code (CLI) / Claude Cowork (Desktop)

Claude Code and Claude Cowork share the same plugin system.

CLI:

/plugin marketplace add dejavu-memory/dejavu
/plugin install dejavu@dejavu-plugins

Cowork desktop app: Open the Cowork tab, click Customize in the sidebar, click Browse plugins, and install Deja Vu.

This installs the full plugin including the MCP server, lifecycle hooks (automatic memory capture), and the Deja Vu SDK skill.

Codex

Option A — Direct MCP (fastest, MCP only):

Codex reads MCP servers from ~/.codex/config.toml as TOML. Add:

[mcp_servers.dejavu]
url = "https://mcp.dejavu.ai/mcp"
bearer_token_env_var = "VENICE_API_KEY"

Export VENICE_API_KEY in your shell and restart Codex. codex mcp add only supports stdio servers, so HTTP servers like Deja Vu's must be added via config.toml directly (or via the Plugins → Connect to a custom MCP → Streamable HTTP UI in the Codex app).

Option B — Sideload the plugin (full experience: MCP + skills + opt-in hooks):

Clone the repo and register the bundled marketplace with one CLI call:

git clone https://github.com/dejavu-memory/dejavu.git ~/codex-plugins/dejavu-source
codex plugin marketplace add ~/codex-plugins/dejavu-source

This points Codex at the repo's .agents/plugins/marketplace.json, which references dejavu-plugin/ as the local source. Restart Codex, run /plugins, and install Deja Vu from the Deja Vu Plugins marketplace.

Don't combine with Option A. The plugin manifest auto-registers dejavu as an MCP server via dejavu-plugin/.codex-mcp.json — adding a manual [mcp_servers.dejavu] block would duplicate the registration.

Optional — enable lifecycle hooks. Codex doesn't auto-wire hooks from plugin manifests; it only reads ~/.codex/hooks.json (or <repo>/.codex/hooks.json) (docs). Run the bundled installer once to merge Deja Vu's entries:

python3 ~/codex-plugins/dejavu-source/dejavu-plugin/scripts/install_codex_hooks.py

This merges three entries into ~/.codex/hooks.json with absolute paths pointing into your clone:

Event	What it does
SessionStart	Loads prior memories as bootstrap context
UserPromptSubmit	Injects relevant memories into the prompt
Stop	Reminds the agent to persist learnings at turn end

Re-running the installer is idempotent (replaces the Deja Vu entries rather than duplicating) and preserves any other hooks you have. To remove: python3 .../install_codex_hooks.py --uninstall. If you move or delete the clone directory, re-run the installer from the new location — the hooks file stores absolute paths.

Codex hooks also require the codex_hooks feature flag in ~/.codex/config.toml:

[features]
codex_hooks = true

The installer prints a reminder if the flag isn't set. Restart Codex after editing the config.

Managing the plugin:

codex plugin marketplace upgrade               # pull latest plugin versions
codex plugin marketplace remove dejavu-plugins   # unregister the marketplace

Cursor

Already have dejavu configured as an MCP server? Remove the existing entry from your Cursor MCP settings before installing to avoid duplicate tools.

Option A — One-click deeplink (installs MCP server only):

Install Deja Vu MCP in Cursor

Option B — Manual configuration (MCP server only):

Add the following to your .cursor/mcp.json:

{
  "mcpServers": {
    "dejavu": {
      "url": "https://mcp.dejavu.ai/mcp/",
      "headers": {
        "Authorization": "Token ${env:VENICE_API_KEY}"
      }
    }
  }
}

Option C — Cursor Marketplace (full plugin with hooks and skills):

Install from the Cursor Marketplace for the complete experience including lifecycle hooks and the Deja Vu SDK skill.

Verify it works

After installing, confirm the MCP server is connected:

1. Start a new session (or restart your current one)
2. Ask: "List my dejavu entities" or "Search my memories for hello"
3. If the dejavu tools appear and respond, you're all set

What's included

Component	Claude Code / Cowork	Cursor (Marketplace)	Cursor (Deeplink/Manual)	Codex (Sideload)	Codex (Direct MCP)
MCP Server	Yes	Yes	Yes	Yes	Yes
Lifecycle Hooks	Yes	Yes	No	Opt-in	No
Deja Vu SDK Skill	Yes	Yes	No	Yes	No
Memory Protocol Skill	No	No	No	Yes	No

• MCP Server — Connects to the Deja Vu remote MCP server (mcp.dejavu.ai), providing tools to add, search, update, and delete memories. No local dependencies required.
• Lifecycle Hooks — Automatic memory capture at key points. Claude Code and Cursor wire hooks up natively when the plugin is installed (session start, context compaction, task completion, session end). Codex hooks are opt-in via a one-time installer (scripts/install_codex_hooks.py) that writes entries into ~/.codex/hooks.json for SessionStart, UserPromptSubmit, and Stop.
• Deja Vu SDK Skill — Guides the AI on how to integrate the Deja Vu SDK (Python & TypeScript) into your applications.
• Memory Protocol Skill — Codex-specific skill that instructs the agent to retrieve relevant memories at task start, store learnings on completion, and capture session state before context loss. Complements the lifecycle hooks on Codex.

Updating the plugin

When the plugin updates (new version pulled from the marketplace, or a fresh local install), the MCP server connection in your existing Claude Code / Cursor / Codex session is left holding a stale handle and stops responding. Restart your client to reconnect:

• Claude Code: run /restart in the prompt, or close and reopen the CLI.
• Cursor: quit and relaunch.
• Codex: restart the editor session.

Your VENICE_API_KEY doesn't need to be re-entered — the auth header is re-read from your environment on the new session. The plugin's MCP config uses ${VENICE_API_KEY} interpolation at session start, not at install time, so as long as the env var is set persistently (in your shell profile or ~/.claude/settings.json env block), reconnection is automatic on restart.

If reconnection still fails after a restart, check that VENICE_API_KEY is reachable in the new shell (echo $VENICE_API_KEY) and confirm you're using a key that starts with m0- (from https://app.dejavu.ai/dashboard/api-keys, not a legacy token).

Optional: tune categories for coding workflows

dejavu auto-tags every memory with one or more categories from a project-level list. The default list is consumer-oriented (food, hobbies, music …) — useful for chat assistants, less so for code. A one-shot script in this plugin replaces it with a coding-focused taxonomy:

# Dry-run first -- prints current vs proposed, no changes:
python dejavu-plugin/scripts/setup_coding_categories.py

# Actually write:
python dejavu-plugin/scripts/setup_coding_categories.py --apply

Requires the dejavu-memory Python SDK (pip install dejavu-memory) and VENICE_API_KEY set. New memories will then auto-tag against architecture_decisions, anti_patterns, task_learnings, tooling_setup, bug_fixes, coding_conventions, user_preferences. Re-run with a different list any time; project.update(custom_categories=[...]) always replaces.

MCP Tools

Once installed, the following tools are available:

Tool	Description
add_memory	Save text or conversation history for a user/agent
search_memories	Semantic search across memories with filters
get_memories	List memories with filters and pagination
get_memory	Retrieve a specific memory by ID
update_memory	Overwrite a memory's text by ID
delete_memory	Delete a single memory by ID
delete_all_memories	Bulk delete all memories in scope
delete_entities	Delete a user/agent/app/run entity and its memories
list_entities	List users/agents/apps/runs stored in Deja Vu

License

Apache-2.0