#1010th of 18 in Memory

everos

Local-first agent memory runtime that stores memories as Markdown files

Stars
13.6k
License
Apache-2.0
Last commit
Oct 2026
Last release
Oct 2026
Language
Python
Stars, last 30 weeks+10,477
27 Mar 2026: 3,105 stars3 Apr 2026: 3,321 stars10 Apr 2026: 3,477 stars17 Apr 2026: 3,818 stars24 Apr 2026: 3,933 stars1 May 2026: 4,057 stars8 May 2026: 4,264 stars15 May 2026: 4,699 stars22 May 2026: 5,416 stars29 May 2026: 5,807 stars5 Jun 2026: 6,799 stars12 Jun 2026: 7,150 stars19 Jun 2026: 7,784 stars26 Jun 2026: 9,048 stars3 Jul 2026: 9,986 stars10 Jul 2026: 10,578 stars17 Jul 2026: 11,045 stars24 Jul 2026: 11,338 stars31 Jul 2026: 11,573 stars7 Aug 2026: 11,715 stars14 Aug 2026: 11,921 stars21 Aug 2026: 12,233 stars28 Aug 2026: 12,445 stars4 Sept 2026: 12,636 stars11 Sept 2026: 12,835 stars18 Sept 2026: 13,004 stars25 Sept 2026: 13,159 stars2 Oct 2026: 13,298 stars9 Oct 2026: 13,371 stars16 Oct 2026: 13,451 stars23 Oct 2026: 13,582 stars

3,105 on 27 Mar 202613,582 on 23 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

EverOS is a Python library and HTTP server that stores agent conversations, files and trajectories as Markdown, then indexes them in SQLite and LanceDB for retrieval. It separates user memory (episodes, profile) from agent memory (cases, skills) and searches by user, agent, app, project and session IDs. A single OpenRouter key enables core add, flush and keyword search; embeddings and rerank unlock hybrid search, reflection and a Knowledge Wiki.

Who it is for: Developers adding persistent, inspectable memory to agents and coding assistants

Ranked among open-source alternatives to Mem (#10 of 10).

Strengths

  • Canonical Markdown files are editable and Git-versionable; a watcher re-syncs indexes after edits
  • No MongoDB, Elasticsearch or Redis needed; storage is Markdown, SQLite and LanceDB
  • Search can be scoped by user_id, agent_id, app_id, project_id and session_id
  • Offline reflection merges episode clusters and refines profiles and skills between sessions

Weaknesses

  • Needs an LLM provider (OpenRouter in the quick start); no fully offline setup is described
  • Hybrid search, reflection and skill extraction require a separate embedding provider
  • Knowledge Wiki and agentic search also need a rerank provider
  • Office file ingestion needs LibreOffice installed on the host; no Docker setup is listed

What it needs

  • no GPU
  • Needs Python 3.12+, OpenRouter API key (or other LLM provider), LibreOffice (office documents only)
  • Models: OpenRouter-hosted LLMs (default openai/gpt-4.1-mini), Optional embedding and rerank providers, Optional multimodal model (default google/gemini-3.8-flash)
  • port 8000

Quick answers

Is everos open source?

Yes. Its code is on GitHub under the Apache-2.0 license.

Does everos need a GPU?

No, it runs without one.

Also in Memory

See all 18
Also in Memory
RankProjectScore
1hindsightAgent memory server with retain, recall and reflect operations53.3k starsMIT94 out of 100
2MemPalaceLocal verbatim memory store for AI agents with semantic search and MCP59.7k starsMIT90 out of 100
3Mem0Long-term memory layer that stores and retrieves user facts for LLM agents Live demo ↗ (opens in a new tab)67.7k starsApache-2.089 out of 100
#4gbrainLong-term memory store for coding agents, with sources and corrections31.1k starsMIT88 out of 100
#5CogneeMemory engine that turns documents and code into a knowledge graph32.7k starsApache-2.085 out of 100