DejaVu — MCP Server by JSingletonAI

by JSingletonAI · MCP Server · ★ 501

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is DejaVu safe to install? View the security audit →

About DejaVu

DejaVu 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. DejaVu 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 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. Quick start That's it. Memories are saved to and searchable immediately. Set your Venice API key DejaVu uses Venice for memory extraction and reasoning. Get a k

agentsailocal-firstmcpmemorypythonsqlite

Quick Facts

Stars501
Forks9
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score66.3372781971754/100
Last Updated2026-07-07
Created2026-05-18
Platformsmcp, python
Est. Tokens~14k

Compatible Skills

These tools work well together with DejaVu for enhanced workflows:

  • mnemo-cortex — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • agentic-context-engine — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
  • vektori — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • Mimir — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • memobase — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

DejaVu alternative? Top 6 similar tools

Looking for a DejaVu alternative? If you're comparing DejaVu with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agentic-context-engine by kayba-ai · ⭐ 2.4k

    🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

  • npcpy by NPC-Worldwide · ⭐ 1.4k

    The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and mor

  • tools by strands-agents · ⭐ 1.1k

    A set of tools that gives agents powerful capabilities.

  • roam-code by Cranot · ⭐ 500

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 comman

  • memov by memovai · ⭐ 160

    Give git-like & traceable memory to OpenClaw and any coding agents. By https://memov.ai/ aka Entire CLI for ev

  • code-graph-rag by vitali87 · ⭐ 2.4k

    The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is DejaVu?

DejaVu is DejaVu — private, portable AI memory powered by Venice and stored locally. It is categorized as a MCP Server with 501 GitHub stars.

What programming language is DejaVu written in?

DejaVu is primarily written in Python. It covers topics such as agents, ai, local-first.

How do I install or use DejaVu?

You can find installation instructions and usage details in the DejaVu GitHub repository at github.com/JSingletonAI/DejaVu. The project has 501 stars and 9 forks, indicating an active community.

What license does DejaVu use?

DejaVu is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to DejaVu?

The top alternatives to DejaVu on Agent Skills Hub include agentic-context-engine, npcpy, tools. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse MCP Server tools