RuVector
RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust.
RuVector is a high-performance vector database and memory system built in Rust that provides persistent, adaptive memory capabilities for AI agents through MCP server integration. It combines local semantic embeddings, vector search, graph relationships, and learning mechanisms to enable agents to remember context across sessions without requiring external API calls. The system supports multiple memory types including episodic, semantic, procedural, and working memory, all accessible through both Rust and Node.js APIs as well as MCP protocol integration.
Key Features
Use Cases
- 01Providing AI agents with persistent memory that survives across conversation sessions and restarts
- 02Building coding assistants that remember project-specific decisions, procedures, and context
- 03Creating knowledge management systems with semantic search over enterprise facts and relationships
- 04Implementing Reflexion-style agents that learn from past episodes and adapt behavior based on outcomes
- 05Developing multi-agent systems with shared collective memory and provenance tracking
- 06Running privacy-compliant AI applications with on-device embeddings and local-only data processing
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
RuVector — FAQ
What is RuVector MCP server?+
RuVector is a vector database and memory system that provides an MCP server interface allowing AI agents to store and retrieve persistent memory including facts, decisions, episodes, and procedures. It runs locally with no external API dependencies for embeddings or search.
How do I install RuVector for MCP integration?+
Install the npm package locally with 'npm install --save-exact ruvector', then start the MCP server with the command shown in the install steps. Configure your MCP client (Claude Desktop, etc.) to connect to the RuVector server using the generated configuration.
Does RuVector require API keys or external services?+
No, RuVector runs entirely locally by default. It downloads the all-MiniLM-L6-v2 embedding model on first use and stores it locally. External embedding providers are optional, and the hosted 'mcp-brain' shared memory service is opt-in only.
Which AI clients work with RuVector?+
RuVector provides an MCP server that works with any MCP-compatible client. It also offers direct Node.js and Rust APIs for custom integrations, plus a browser WASM package and PostgreSQL extension.
Is RuVector free to use?+
Yes, RuVector is open source and available under the MIT License. All core functionality including local embeddings and vector search is free with no usage limits.
What are the system requirements?+
For Node.js usage, you need Node.js installed and support for native binaries (Linux x64/arm64, macOS x64/arm64, Windows x64). For Rust development, Rust 1.77 or newer is required. The default embedding model downloads approximately 80MB on first use.
How do I install RuVector?+
Open the source repository on GitHub and follow its README. RuVector is a mcp server — MCP Agents Market links you directly to the official repo.
Is RuVector free?+
RuVector is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.