</>MCP Agents Market
Plugin

EverOS

by EverMind-AI12.3kPythonUpdated 2026-08-17

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Claude CodeCursorWindsurfCodex

EverOS is a Claude Code plugin and local-first memory runtime that provides persistent, cross-session memory for AI coding assistants and agents. It stores conversations, files, and agent trajectories as human-readable Markdown files, synchronized with SQLite and LanceDB indexes for fast retrieval. The plugin automatically saves coding session context and recalls relevant information across sessions, eliminating the need to re-explain project details. Built on a Markdown-first architecture, all memories remain user-owned, editable, Git-versionable, and portable across different AI tools and workflows.

Key Features

Markdown-native storage: all memories saved as readable, editable .md files that can be version-controlled with Git
Local-first architecture: runs entirely on your machine with SQLite + LanceDB indexes, no cloud dependencies required
Cross-session context retention: automatically saves and recalls coding context, project preferences, and past solutions
Multi-dimensional retrieval: search by user_id, agent_id, app_id, project_id, and session_id for precise context filtering
Self-evolving memory: offline reflection process merges episode clusters and refines profiles between sessions
Multimodal ingestion: parse and remember images, PDFs, audio, and office documents alongside code and text
Knowledge Wiki: editable Markdown knowledge pages with taxonomy, CRUD APIs, and topic search
Hybrid search modes: keyword, vector, and hybrid retrieval with configurable embedding and rerank providers

Use Cases

  • 01Persistent memory for Claude Code and other AI coding assistants across multiple projects
  • 02Multi-agent orchestration where coordinated agents share a common memory layer
  • 03Personal coding assistant that remembers your preferences, coding patterns, and project contexts
  • 04Browser automation agents with memory of previous web interactions and extracted data
  • 05Educational assistants that build cumulative knowledge of student progress and learning patterns
  • 06Long-running research projects where AI needs to recall insights from weeks or months ago

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.1k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin84.9k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.1k

EverOS — FAQ

What is EverOS and how does it work with Claude Code?+

EverOS is a local memory runtime that gives Claude Code and other AI coding assistants persistent, cross-session memory. It stores conversations and context as Markdown files that are automatically indexed and recalled when relevant, so you don't have to re-explain your project every session.

How do I install EverOS for Claude Code?+

Install EverOS via pip (pip install everos), run 'everos init' to create the config, add your OpenRouter API key to ~/.everos/everos.toml, then start the server with 'everos server start'. The Claude Code plugin code is in the use-cases/claude-code-plugin directory of the repository.

Which AI coding assistants and clients work with EverOS?+

EverOS works with Claude Code, Cursor, Windsurf, Codex, and any AI assistant that can integrate with its REST API. The repository includes examples for Claude Code specifically, plus integrations for browser agents, multi-agent systems, and custom workflows.

Do I need API keys or paid services to use EverOS?+

You need at least one OpenRouter API key for basic functionality (keyword search and memory storage). Optional embedding and rerank providers unlock hybrid search and advanced features, but the core memory flow works with just OpenRouter.

Is EverOS free and open source?+

Yes, EverOS is open source under the Apache License 2.0. The software itself is free, but you'll pay for API usage through providers like OpenRouter based on your chosen models and volume.

What are the system requirements and dependencies?+

EverOS requires Python 3.12+ and one OpenRouter API key for basic use. For multimodal file parsing (PDF, images, office documents), install the [multimodal] extra; office document support additionally requires LibreOffice installed on your system.

How do I install EverOS?+

Open the source repository on GitHub and follow its README. EverOS is a plugin — MCP Agents Market links you directly to the official repo.

Is EverOS free?+

EverOS is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Knowledge & Memory PluginsDeveloper Tools PluginsProductivity & Workflow PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories