EverOS
installs/mo · pypistarsforks
How to install EverOS?
evermind-ai/everos
$git clone https://github.com/EverMind-AI/EverOSWebsite · Documentation · Blog · 中文
README.md
| 1 | <div align="center" id="readme-top"> |
| 2 | |
| 3 |  |
| 4 | |
| 5 | <p align="center"> |
| 6 | <a href="https://x.com/evermind"><img src="https://img.shields.io/badge/EverMind-000000?labelColor=gray&style=for-the-badge&logo=x&logoColor=white" alt="X"></a> |
| 7 | <a href="https://huggingface.co/EverMind-AI"><img src="https://img.shields.io/badge/🤗_HuggingFace-EverMind-F5C842?labelColor=gray&style=for-the-badge" alt="HuggingFace"></a> |
| 8 | <a href="https://discord.gg/gYep5nQRZJ"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2FgYep5nQRZJ%3Fwith_counts%3Dtrue&query=%24.approximate_presence_count&suffix=%20online&label=Discord&color=404EED&labelColor=gray&style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a> |
| 9 | <a href="https://github.com/EverMind-AI/EverOS/discussions/67"><img src="https://img.shields.io/badge/WeCom-EverMind_社区-07C160?labelColor=gray&style=for-the-badge&logo=wechat&logoColor=white" alt="WeChat"></a> |
| 10 | </p> |
| 11 | |
| 12 | [Website](https://evermind.ai) · [Documentation](https://docs.evermind.ai) · [Blog](https://evermind.ai/blogs) · [中文](README.zh-CN.md) |
| 13 | |
| 14 | </div> |
| 15 | |
| 16 | |
| 17 | <br> |
| 18 | |
| 19 | <details> |
| 20 | <summary><kbd>Table of Contents</kbd></summary> |
| 21 | |
| 22 | <br> |
| 23 | |
| 24 | - [Why Ever OS](#why-ever-os) |
| 25 | - [Quick Start](#quick-start) |
| 26 | - [Use Cases](#use-cases) |
| 27 | - [Documentation](#documentation) |
| 28 | - [Star Us](#star-us) |
| 29 | - [EverMind Ecosystems](#evermind-ecosystems) |
| 30 | - [Contributing](#contributing) |
| 31 | |
| 32 | <br> |
| 33 | |
| 34 | </details> |
| 35 | |
| 36 | |
| 37 | ## Why Ever OS |
| 38 | |
| 39 | EverOS is a Python library and local-first memory runtime for agents and |
| 40 | makers. It gives one portable memory layer across coding assistants, apps, |
| 41 | devices, and workflows from day one. It stores conversations, files, and agent |
| 42 | trajectories as readable Markdown, then syncs local SQLite and LanceDB indexes |
| 43 | for fast retrieval and self-evolving reuse. |
| 44 | |
| 45 | <table> |
| 46 | <tr> |
| 47 | <th width="28%">Title</th> |
| 48 | <th width="36%">EverOS</th> |
| 49 | <th width="36%">Other Agent Memory Libraries</th> |
| 50 | </tr> |
| 51 | <tr> |
| 52 | <td><strong>Markdown source of truth</strong></td> |
| 53 | <td>✅ Canonical <code>.md</code> files that are readable, editable, diffable, and Git-versioned</td> |
| 54 | <td>❌ Usually API, vector, graph, dashboard, or database state</td> |
| 55 | </tr> |
| 56 | <tr> |
| 57 | <td><strong>Direct file editing</strong></td> |
| 58 | <td>✅ Edit <code>.md</code> files; cascade watcher syncs</td> |
| 59 | <td>❌ Usually SDK, API, dashboard, or backend update paths</td> |
| 60 | </tr> |
| 61 | <tr> |
| 62 | <td><strong>Local three-part stack</strong></td> |
| 63 | <td>✅ Markdown + SQLite + LanceDB; no MongoDB, Elasticsearch, or Redis required</td> |
| 64 | <td>❌ Often depends on managed services, vector DBs, graph DBs, or server stacks</td> |
| 65 | </tr> |
| 66 | <tr> |
| 67 | <td><strong>User + agent tracks</strong></td> |
| 68 | <td>✅ User <code>episodes/profile</code> and agent <code>cases/skills</code> are separate first-class surfaces</td> |
| 69 | <td>❌ Usually centered on chat history, profiles, entities, facts, or retrieval records</td> |
| 70 | </tr> |
| 71 | <tr> |
| 72 | <td><strong>Orthogonal retrieval</strong></td> |
| 73 | <td>✅ Search by <code>user_id</code>, <code>agent_id</code>, <code>app_id</code>, <code>project_id</code>, and <code>session_id</code></td> |
| 74 | <td>❌ Usually app, namespace, tenant, thread, or graph scoped</td> |
| 75 | </tr> |
| 76 | <tr> |
| 77 | <td><strong>Knowledge Wiki</strong></td> |
| 78 | <td>✅ Editable, source-backed Markdown knowledge pages with taxonomy, CRUD APIs, and topic search</td> |
| 79 | <td>❌ Usually separate from memory, trapped in a dashboard, or not tied back to source files</td> |
| 80 | </tr> |
| 81 | <tr> |
| 82 | <td><strong>Reflection</strong></td> |
| 83 | <td>✅ Offline memory evolution that merges episode clusters and refines profiles and skills between sessions</td> |
| 84 | <td>❌ Usually retrieval-only memory with little background consolidation or long-horizon improvement</td> |
| 85 | </tr> |
| 86 | </table> |
| 87 | |
| 88 | <br> |
| 89 | |
| 90 | ## Quick Start |
| 91 | |
| 92 | > Goal: play with the memory visualizer first, then start EverOS, write one |
| 93 | > real memory, and search it back. |
| 94 | |
| 95 | ### 0. Prerequisites |
| 96 | |
| 97 | - Python 3.12+ |
| 98 | - No API keys are needed for `everos demo`. |
| 99 | - To run the real server-backed memory flow, create two provider keys |
People who liked this also viewed
6 picksType
- excel-mcpA Model Context Protocol (MCP) server for working with Excel (.xlsx) files without requiring Microsoft Excel. Enables AI assistants to create, read, modify, and format spreadsheets using openpyxl, fully in Python and cross-platform.MCP ServersOct 2025
- memories-with-lessons-mcp-serverI enhance the existing memory mcp server from the official mcp github, so big thanks and credits for creating thisMCP ServersFeb 2025
- anytype-mcpAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.MCP ServersJul 2026
- mcp-server-kubernetesMCP Server for kubernetes management commandsMCP ServersJul 2026
- thoughtboxThoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.MCP ServersJul 2026
- google-drive-mcpA Model Context Protocol (MCP) server that provides secure integration with Google Drive, Docs, Sheets, Slides and Calendar. It allows Claude Desktop and other MCP clients to manage files in Google Drive through a standardized interface.MCP ServersJul 2026
