by JSingletonAI · MCP Server · ★ 501
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.
| Stars | 501 |
| Forks | 9 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 66.3372781971754/100 |
| Last Updated | 2026-07-07 |
| Created | 2026-05-18 |
| Platforms | mcp, python |
| Est. Tokens | ~14k |
These tools work well together with DejaVu for enhanced workflows:
Explore other popular mcp server tools:
DejaVu is DejaVu — private, portable AI memory powered by Venice and stored locally. It is categorized as a MCP Server with 501 GitHub stars.
DejaVu is primarily written in Python. It covers topics such as agents, ai, local-first.
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.
DejaVu is released under the Apache-2.0 license, making it free to use and modify according to the license terms.