Back to directory

EverOS

A Python library and local-first memory runtime that gives coding assistants and other agents one portable memory layer across apps and devices, stored as readable, Git-versioned Markdown.

EverOS

EverOS is a Python library and local-first memory runtime that gives agents and their users one portable memory layer across coding assistants, apps, devices and workflows. It stores conversations, files and agent trajectories as plain Markdown, which stays readable, editable and diffable and can be versioned with Git, and syncs local SQLite and LanceDB indexes from those files for fast retrieval.

Files can be edited directly, with a watcher keeping the index in step, and it keeps a user's own episodes and profile separate from an agent's own cases and skills, as distinct first-class kinds of memory that can each be searched by user, agent, app, project or session. An editable, source-backed knowledge wiki sits alongside the memory store with its own topic search, and an offline reflection process merges episode clusters and refines profiles and skills between sessions rather than only retrieving what was already written.

It integrates with DeepSeek Harness, Hermes, OpenClaw, Raven and Dify, comes built into Raven, and starts with a single OpenRouter API key, installed with pip or uv on Python 3.12 or later.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.