EverOS

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

What is EverOS?

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

Overview of EverOS

What it is

EverOS is a Python library and local-first memory runtime for AI agents and makers. It provides a portable memory layer that works across coding assistants, apps, devices, and workflows. The system stores conversations, files, and agent trajectories as readable Markdown files, then syncs local SQLite and LanceDB indexes for fast retrieval and self-evolving reuse.

Key features

  • Markdown-native: Canonical .md files that are readable, editable, diffable, and Git-versioned.
  • Local three-part stack: Markdown + SQLite + LanceDB; no MongoDB, Elasticsearch, or Redis required.
  • User + agent tracks: User episodes/profile and agent cases/skills are separate first-class surfaces.
  • Orthogonal retrieval: Search by user_id, agent_id, app_id, project_id, and session_id.
  • Knowledge Wiki: Editable, source-backed Markdown knowledge pages with taxonomy, CRUD APIs, and topic search.
  • Reflection: Offline memory evolution that merges episode clusters and refines profiles and skills between sessions.

Use cases

EverOS adds durable memory to agent and workflow platforms. It can be used with DeepSeek Harness, Hermes, OpenClaw, Raven, Dify, and other integrations. Typical use cases include storing and retrieving agent conversation history, maintaining user profiles, building knowledge bases from source files, and enabling long-horizon memory improvement across sessions.

Getting started

### Install
uv pip install everos
### or: pip install everos

### Try the standalone demo (no API key required)
everos demo

### Initialize and add your OpenRouter API key
everos init

### Start the server
everos server start

### Check health
curl http://127.0.0.1:8000/health

See the repository README for detailed setup and API usage.

License and pricing

License: Apache-2.0. Pricing: open source (free).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/evermind-aieveros.svg)](https://yunodb.com/tools/evermind-aieveros?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/evermind-aieveros?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/evermind-aieveros.svg" alt="Featured on YunoDB" height="20"></a>