Apache-2.0 local-first, Markdown-native agent memory runtime; DeepSeek Harness connects via the local HTTP API (/api/v2) or MCP bridges to gain persistent long-term memory.
DSH integration
Compatible
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
Apache-2.0
01What can it help you accomplish?
Give DeepSeek Harness sessions persistent long-term memory
Durable memories stored as readable Markdown under ~/.everos, with local SQLite and LanceDB indexes and keyword search recall via the local HTTP API
Developers running DeepSeek Harness (dsh) or other coding agents who want cross-session context that survives restarts
Try the memory ingest -> extract -> index -> recall loop in minutes
A running local server with one-key setup: memory add, flush, Markdown persistence, cascade indexing, and keyword search
Builders evaluating agent memory options who want a no-infrastructure trial before committing
Ingest multimodal content into agent memory
Image, PDF, audio, and office-file ingestion through /api/v2/memory/add via the optional multimodal extra
Teams whose agent context includes documents, screenshots, and audio rather than plain text
02How to install into DeepSeek Harness
Prerequisites
- Python 3.12+
- One OpenRouter API key (https://openrouter.ai/keys)
Installation steps
- 01
Install the package: `uv pip install everos` (or `pip install everos`)
- 02
Run `everos init` — this creates `~/.everos/everos.toml` and `~/.everos/ome.toml`; replace the empty `api_key` in `~/.everos/everos.toml` with your OpenRouter key (use `everos init --root <path>` for a different memory root)
- 03
Start the server: `everos server start`
- 04
Add memories and search them via the HTTP API, e.g. POST /api/v2/memory/add, /api/v2/memory/flush, /api/v2/memory/search (use `"method": "keyword"` in the one-key setup)
- 05
Optional: `uv pip install 'everos[multimodal]'` for image / PDF / audio / office-file ingestion
Verify the integration
- Open a second terminal and run `curl http://127.0.0.1:8000/health` — look for `"status":"ok"`; with the one-key setup `capabilities.llm` is `true` while embedding and rerank remain `false`
- Add a tiny conversation via /api/v2/memory/add, flush it, then search it back via /api/v2/memory/search — you should see the stored memory in the response
03DSH integration and capability boundaries
Local-first memory server that DeepSeek Harness can call through the local HTTP API (/api/v2/memory/add, /flush, /search) or community MCP bridges; the README documents EverOS as a universal long-term memory layer for AI coding assistants
Markdown-native memory persistence
conversations, files, and agent trajectories→canonical readable/editable/diffable .md files under the memory root (~/.everos), Git-versionable
writes Markdown files and syncs local SQLite and LanceDB indexes on diskcascade watcher re-syncs indexes when you edit .md files directlyLocal HTTP memory API with orthogonal retrieval
memory add / flush / search requests with user_id, agent_id, app_id, project_id, session_id→keyword (Tier 1) or hybrid search results from the local index; business endpoints live under /api/v2
starts a local server on 127.0.0.1:8000sends prompts to the configured OpenRouter endpoint when the llm capability is enabledTiered capability upgrades (embedding / rerank / multimodal)
optional [embedding], [rerank], [multimodal] sections in everos.toml→hybrid search, reflection and skill extraction; agentic search and Knowledge Wiki; image / PDF / audio / office ingestion
extra providers mean additional API calls and costsmultimodal extra pulls in everalgo-parser; office documents additionally require LibreOffice as a system dependencyOffline reflection (self-evolving memory)
accumulated episode clusters between sessions→merged episodes and refined user profiles and agent skills without online traffic
requires an embedding provider to be configured; mutates stored memory state during consolidation
04Who is it for? When not to use it?
Good for
- Developers running DeepSeek Harness (dsh) or other coding agents who want cross-session context that survives restarts
- Builders evaluating agent memory options who want a no-infrastructure trial before committing
- Teams whose agent context includes documents, screenshots, and audio rather than plain text
Not for
- The one-key OpenRouter setup is Tier 1 only (memory add/flush, Markdown persistence, cascade indexing, keyword search). Hybrid search defaults require an embedding provider, and unconfigured features return HTTP 422.
05Compatibility, maintenance and safety notes
- The one-key OpenRouter setup is Tier 1 only (memory add/flush, Markdown persistence, cascade indexing, keyword search). Hybrid search defaults require an embedding provider, and unconfigured features return HTTP 422.
- Office document ingestion (.doc/.docx/.ppt/.pptx/.xls/.xlsx) requires LibreOffice installed on the host; without it, office uploads return HTTP 415 (PDF/image/audio/HTML/email parsing is unaffected).
- Core flows require Python 3.12+ and a paid OpenRouter API key stored in ~/.everos/everos.toml; the README does not document a fully offline (key-less) production mode beyond the educational demo.
Apache-2.0 · actively maintained (latest release v1.2.3, 2026-08-07)
06Frequently asked questions
How do I connect DeepSeek Harness to EverOS?
Run EverOS as a local memory server (`everos server start`) and call its HTTP API — /api/v2/memory/add, /api/v2/memory/flush, /api/v2/memory/search — from your dsh workflow. The README positions EverOS as a universal long-term memory layer for AI coding assistants, with example integrations and MCP-style bridges in its use-case gallery.
What do I need before installing?
Python 3.12+ and one OpenRouter API key. The standalone `everos demo` runs without any key if you just want to try the ingest -> extract -> index -> recall loop first.
Where does my memory data live?
Locally, under ~/.everos (or a custom path via `everos init --root <path>`). Everything is persisted as readable, editable Markdown files with local SQLite and LanceDB indexes — no MongoDB, Elasticsearch, or Redis required.
What are the limits of the one-key setup?
Tier 1 covers server startup, memory add/flush, Markdown persistence, cascade indexing, and keyword search. Hybrid search, reflection, and Knowledge Wiki need extra embedding/rerank providers; missing capabilities are reported by /health and unconfigured features return HTTP 422.
Can it ingest files and documents?
Yes, with the optional `everos[multimodal]` extra: images, PDFs, audio, HTML, email, and office documents. Office formats additionally require LibreOffice installed on the host, otherwise uploads return HTTP 415.
07Related DSH workflows
ruflo
by ruvnet
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
reactive-resume
by amruthpillai
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
yao
by yaoapp
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
openpencil
by zseven-w
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.
08Data and sources
Universal long-term memory layer for AI coding assistants, powered by EverOS.
EverOS is a Python library and local-first memory runtime for agents and makers. It gives one portable memory layer acro…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.