Everos
Build, evaluate, and integrate long-term memory for self-evolving agents.
What is Everos?
Everos is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to build, evaluate, and integrate long-term memory for self-evolving agents.
Build, evaluate, and integrate long-term memory for self-evolving agents.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Build, evaluate, and integrate long-term memory for self-evo
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx everosConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Everos
EverOS is a long-term memory framework for self-evolving AI agents, providing hybrid retrieval combining BM25, vector similarity, and scalar filtering to build persistent, searchable memory stores from conversations and agent trajectories. It uses a dual-track memory architecture that maintains separate stores for agent memory (cases and skills) and user memory (episodes and profile), with local-first storage using Markdown, SQLite, and LanceDB. AI developers and researchers use it to give agents the ability to remember past interactions, accumulate skills over time, and retrieve relevant context from long-running deployments.
Prerequisites
- Python 3.10+ installed on your system
- UV package manager (pip install uv) or pip
- API keys for an OpenAI-compatible LLM provider (OpenAI, OpenRouter, vLLM, Ollama, or DeepInfra)
- LibreOffice installed if using multimodal support for office documents (.docx, .pptx, .xlsx)
- An MCP-compatible client to interface with the memory server
Install EverOS
Install the core package via pip or uv. Add the [multimodal] extra if you need to process images, audio, PDFs, and Office documents.
pip install everos
# or with multimodal support:
pip install 'everos[multimodal]'Initialize the configuration file
Run everos init to generate a .env file with all required configuration keys. Use --xdg to store config in the standard XDG config directory instead of the current directory.
everos init
# or store in ~/.config/everos/.env:
everos init --xdgConfigure your LLM provider credentials
Edit the generated .env file to add your API keys. EverOS supports any OpenAI-protocol compatible endpoint — set the BASE_URL variables to point to your chosen provider.
# Example .env entries for OpenAI:
LLM__API_KEY=sk-your-openai-api-key
LLM__MODEL=gpt-4o-mini
EMBEDDING__API_KEY=sk-your-openai-api-key
EMBEDDING__MODEL=text-embedding-3-smallStart the EverOS server
Launch the memory server. It exposes an OpenAI-protocol compatible HTTP API for memory operations.
everos server startConnect your MCP client
Add EverOS to your MCP client configuration to enable memory tools in your AI assistant.
{
"mcpServers": {
"everos": {
"command": "npx",
"args": ["everos"]
}
}
}Everos Examples
Client configuration
MCP client configuration for connecting to the EverOS long-term memory server.
{
"mcpServers": {
"everos": {
"command": "npx",
"args": ["everos"]
}
}
}Prompts to try
Store, retrieve, and manage long-term memory for AI agents using EverOS's hybrid retrieval system.
- "Store this conversation as an episode in my long-term memory with tags: project-alpha, planning"
- "Retrieve all memories related to the 'database migration' project from last month"
- "What skills has this agent accumulated for handling Python debugging tasks?"
- "Search my memory for any past interactions about API rate limiting and summarize the solutions found"
- "Update my user profile to remember that I prefer concise responses and use Python for scripting"Troubleshooting Everos
everos init fails or .env file is not created
Ensure you have write permissions in the current directory. Use 'everos init --xdg' to write to the user config directory (~/.config/everos/.env) instead. Verify the package installed correctly with 'everos --version'.
Server starts but LLM API calls fail with authentication errors
Open the .env file and ensure all four API key placeholders are filled in with valid keys. The file contains slots for both LLM and embedding model keys. For OpenRouter, set the BASE_URL variables: 'LLM__BASE_URL=https://openrouter.ai/api/v1'.
Multimodal document processing fails with LibreOffice errors
Office document conversion (.docx, .pptx, .xlsx) requires LibreOffice installed as a system dependency. Install it with 'brew install --cask libreoffice' on macOS or 'apt-get install libreoffice' on Ubuntu, then restart the EverOS server.
Frequently Asked Questions about Everos
What is Everos?
Everos is a Model Context Protocol (MCP) server that build, evaluate, and integrate long-term memory for self-evolving agents. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Everos?
Follow the installation instructions on the Everos GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Everos?
Everos works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Everos free to use?
Yes, Everos is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Everos Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Everos? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Cipher
★ 4.8kCipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS's Kiro, VS Code, and Roo Code through MCP, and coding agents, such as Kimi K2.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Everos in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Everos?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.