LocalRecall
:brain: 100% Local Memory layer and Knowledge base for agents with WebUI
LocalRecall MCP server provides AI agents with a fully local memory layer and knowledge base through the Model Context Protocol. It enables agents to store, retrieve, and search documents using vector databases (Chromem or PostgreSQL) without requiring cloud services or GPUs. The MCP integration offers tools for searching collections, managing documents, and organizing knowledge bases through a RESTful API with an intuitive web UI.
Key Features
Use Cases
- 01Providing long-term and short-term memory capabilities for AI agents and chatbots
- 02Building RAG applications with local document embeddings and semantic search
- 03Creating private knowledge bases for agents that operate in air-gapped or offline environments
- 04Integrating with LocalAI and LocalAGI agent frameworks for enhanced memory management
- 05Managing agent context across conversations with persistent vector storage
- 06Automating knowledge updates by monitoring Git repositories and website content
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.
LocalRecall — FAQ
What is the LocalRecall MCP server?+
LocalRecall MCP server is a Model Context Protocol integration that provides AI agents with local memory and knowledge base capabilities. It offers tools for searching documents, managing collections, and uploading content to vector databases, all running completely offline without cloud dependencies.
How do I install and connect the LocalRecall MCP server?+
Run LocalRecall using Docker with the pre-built image from quay.io/mudler/localrecall, then configure the MCP server by running the ghcr.io/mudler/mcps/localrecall container with your LocalRecall URL and optional API key. You can enable specific MCP tools using the LOCALRECALL_ENABLED_TOOLS environment variable.
Which AI clients work with LocalRecall MCP server?+
LocalRecall integrates with any MCP-compatible client and is specifically designed to work with LocalAI and LocalAGI agent frameworks. The MCP server can be configured to connect from any client that supports the Model Context Protocol.
Do I need API keys or external services to use LocalRecall?+
LocalRecall requires an OpenAI-compatible API endpoint for generating embeddings (such as LocalAI), but no external cloud services or API keys are required. You can optionally secure LocalRecall itself with API keys by setting the API_KEYS environment variable.
Is LocalRecall free and open source?+
Yes, LocalRecall is released under the MIT License and is completely free and open source. All code is available on GitHub and pre-built Docker images are provided for easy deployment.
What are the prerequisites for running LocalRecall?+
You need either Go 1.16+ for building from source or Docker for containerized deployment. You also need access to an OpenAI-compatible embedding service (like LocalAI) to generate vector embeddings for documents.
How do I install LocalRecall?+
Open the source repository on GitHub and follow its README. LocalRecall is a mcp server — MCP Agents Market links you directly to the official repo.
Is LocalRecall free?+
LocalRecall is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.