EverMind-AI/EverOS
EverOS is a tool for DeepSeek Harness. One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
REVIEW SCORECARD
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
A mature, actively maintained local-first memory layer with strong docs and a clean pip install, worth adopting for agen
README documents a clear three-part stack (Markdown + SQLite + LanceDB), Python 3.12+ requirement, and both uv and pip install paths, though no test or CI details are visible in the excerpt.
The install path is a standard `pip install everos` with no download-and-execute scripts or plaintext credential handling shown, but the README requires an OpenRouter API key and gives no detail on how it is stored, so this is a neutral assessment.
It targets a real and common pain point—portable, user-owned long-term memory across agents and tools—with concrete features like orthogonal retrieval by user/agent/app/project/session IDs and offline reflection.
Last updated 2026-08-26 with 12,438 stars, an Apache-2.0 license, and an active ecosystem of integrations (DeepSeek Harness, Hermes, OpenClaw, Raven, Dify), indicating ongoing development.
The README provides a table of contents, a comparison table, prerequisites, a no-key demo command, and links to a dedicated documentation site, though the excerpt cuts off mid-quick-start.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
pip install everosThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
VALIDATION LADDER
FAQ
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
EverOS has 12,438 stars and 903 forks on GitHub, last updated 2026-08-26.
EverOS is distributed under the Apache-2.0 license.
EverOS is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:clawdbot-skill、skills、agent-memory、chats、long-term-memory、mcp、memory、memory-management、rag。
MemTensor
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
HarnessRouter
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
zilliztech
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
huiliyi37
Tianshu is a terminal coding agent runtime built on the harness project (Tui X Gui), with prefix-cache engineering optimization for DeepSeek V4 (measured steady-state hit rate of 97–99% in long sessions) and deep adaptation. It breaks out of the traditional AI coding assistant's limit of treating the LLM merely as a tool, and is built on a cognitive virtual machine (CVM), a self-awareness layer and Stigmergy self-decaying memory, making the AI a development partner with independent judgment and cognitive safeguards.
liustack
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 The strongest free web search plugin for DeepSeek Harness across the web, free with no signup and no API key. Adds search for models without web access; ask the web or X and get structured JSON evidence (search, scrape, cite).
omdsh-dev
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.