Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By JSingletonAI
Add persistent memory and personalization to AI applications with semantic search, guided memory recall, and automatic context management for Claude workflows.
npx claudepluginhub jsingletonai/dejavu --plugin dejavuDeja Vu memory protocol for agents using the dejavu MCP tools (Claude Code, Cursor, Codex, and any other MCP-aware runtime). Decide deliberately when memory context would help, run targeted searches with metadata filters when it would, and store key learnings as work completes. Use the dejavu MCP tools (add_memory, search_memories, get_memories, etc.) for all memory operations.
Deja Vu Platform SDK for adding persistent memory to AI applications. TRIGGER when: user mentions "dejavu", "MemoryClient", "memory layer", "remember user preferences", "persistent context", "personalization", or needs to add long-term memory to chatbots, agents, or AI apps. Covers Python SDK (dejavu-memory), TypeScript SDK (dejavu-memory), and framework integrations (LangChain, CrewAI, OpenAI Agents SDK, Pipecat, LlamaIndex, AutoGen, LangGraph). Also covers the open-source self-hosted Memory class. This is the DEFAULT dejavu skill for ambiguous queries. DO NOT TRIGGER when: user asks about CLI commands, terminal usage, or shell scripts (use dejavu-cli), or Vercel AI SDK / @dejavu/vercel-ai-provider / createDeja Vu (use dejavu-vercel-ai-sdk).
Modifies files
Hook triggers on file write and edit operations
External network access
Connects to servers outside your machine
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows using the Mem0 Platform MCP server.
Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
v9.40.3 — Hardened multi-LLM council with extracted benchmark routing, capability-aware role fit, CLI-visible warnings, diversity, veto, quorum, and implementation gates. Run /octo:setup.
Plugin that includes the Figma MCP server and Skills for common workflows
Local-first AI memory for agents and assistants.
Your AI tools forget everything between sessions. The ones that don't store your context on someone else's servers. Deja Vu is the third option — a memory layer that runs on your machine, in SQLite, and plugs into anything that speaks Python, REST, CLI, or MCP.
One memory store, every tool. Add a preference from the CLI, retrieve it in Claude Desktop, query it from a Python agent — same database, no sync, no account. Context built up in one tool is immediately available in the next.
Private by default. Memories live in ~/.dejavu on your machine. The only thing that leaves is the LLM call itself, routed through Venice's privacy-focused API. No telemetry, no hosted memory service, no vendor lock-in. Open the SQLite file with any client and inspect every byte.
pip install dejavu-memory
dejavu init
dejavu add "I prefer concise technical explanations"
dejavu search "How should responses be written for me?"
That's it. Memories are saved to ~/.dejavu/ and searchable immediately.
Deja Vu uses Venice for memory extraction and reasoning. Get a key at venice.ai and export it:
export VENICE_API_KEY="your-key"
from dejavu import Memory
memory = Memory()
memory.add("I prefer local-first tools.", user_id="local_user")
results = memory.search("What tools do I prefer?", user_id="local_user")
print(results)
dejavu serve
curl http://127.0.0.1:8765/health
Runs on 127.0.0.1 by default — not exposed to your network.
Deja Vu is three layers: an interface layer (Python, CLI, REST, MCP), a memory engine that extracts and ranks what's worth remembering, and a local SQLite store. Venice handles the LLM calls for extraction and search — everything else runs on your machine.
When you add a memory, the engine asks Venice to pull out durable facts and preferences from the raw text, then writes them to SQLite with embeddings. When you search, it embeds the query, pulls the closest matches, and optionally re-ranks them through Venice for relevance.
Every interface hits the same engine and the same store. Add a memory through the CLI, retrieve it from Claude Desktop over MCP — same database, no sync.
Run Deja Vu as an MCP server so local agents and editors share the same memory store.
{
"mcpServers": {
"dejavu": {
"command": "dejavu",
"args": ["mcp"],
"env": {
"VENICE_API_KEY": "your-key"
}
}
}
}
Drop this into your Claude Desktop, Cursor, or any MCP-compatible client config.
| Interface | Use it for |
|---|---|
| Python SDK | Embedding memory directly into agents and scripts |
CLI (dejavu) | Quick adds, searches, and inspection from the terminal |
| REST API | Language-agnostic access, local services, internal tools |
| MCP server | Sharing one memory store across Claude Desktop, Cursor, and other MCP clients |
~/.dejavuDeja Vu writes everything to ~/.dejavu/:
~/.dejavu/
├── config.json ← Venice key, model choices, local settings
├── memories.db ← SQLite store: memories, embeddings, metadata
└── logs/ ← request logs (off by default, opt-in via config)
The repo itself:
dejavu/ ← core Python SDK and local memory engine
cli/ ← Python and Node CLIs
docs/ ← documentation
examples/ ← demo apps and integration samples
tests/ ← SDK and interface tests
The goal is to make AI memory feel boring and dependable: easy to run, easy to inspect, and easy to move between tools. The design follows the white paper's long-term memory direction while keeping the first public version focused on the parts people can actually use right away.
Deja Vu is based on the open-source work from mem0ai/mem0 and is licensed under Apache-2.0.