Everos

v1.0.0Knowledge & Memorystable

Build, evaluate, and integrate long-term memory for self-evolving agents.

agent-memoryagentic-aiaichatsclawdbot
Share:
5,446
Stars
0
Downloads
0
Weekly
0/5

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

Build long-term memory for self-evolving agents
Manage agent memory integration and evaluation
EverMind-AI

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx everos

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

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
1

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]'
2

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 --xdg
3

Configure 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-small
4

Start the EverOS server

Launch the memory server. It exposes an OpenAI-protocol compatible HTTP API for memory operations.

everos server start
5

Connect 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.

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.

Quick Config Preview

{ "mcpServers": { "everos": { "command": "npx", "args": ["-y", "everos"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

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.

33,000+ ServersFree & Open SourceStep-by-Step Guides